cslt Wiki - 用户贡献 [zh-cn]

ASR Status Report 2017-2-27

2017-02-28T04:58:14Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.2.27

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
* Run 3-layer joint training network, do some visualization work and try residual network.
[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=luohang&step=view_request&cvssid=598]
||
* Compared ASR model in joint traning model with ASR model given fixed LID projection.
|-

|-
|Ying Shi
||
*
||
*
|-

|-
|Yixiang Chen
||
* Submit results of ASVspoofing challenge.
||
* ASVspoofing -- Waiting for the key files of eva set.
|-

|-
|Lantian Li
||
* Submit results of ASVspoofing challenge [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=590].
* Write book -- Done.
||
* Deep speaker embedding.
|-

|-
|Zhiyuan Tang
||
* explore sub-questions,[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=595 baselines]
* poster for ICASSP17
||
* continue exploring sub-questions
|-

|}

-------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.2.20

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
|-

|-
|Yixiang Chen
||
* ASVspoofing challenge.
||
* ASVspoofing.
|-

|-
|Lantian Li
||
* Deep speaker embedding [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=591]
* ASVspoofing [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=590]
* Write book.
||
* ASVspoofing
|-

|-
|Zhiyuan Tang
||
* joint training of speech and language recognition, two languages for preliminary exploration,[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=595 baselines]
||
* explore sub-questions
|-

|}

ASR Status Report 2017-2-27

2017-02-28T04:57:13Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.2.27

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
* Run 3-layer joint training network, do some visualization work and try residual network.
||
* Compared ASR model in joint traning model with ASR model given fixed LID projection.
|-

|-
|Ying Shi
||
*
||
*
|-

|-
|Yixiang Chen
||
* Submit results of ASVspoofing challenge.
||
* ASVspoofing -- Waiting for the key files of eva set.
|-

|-
|Lantian Li
||
* Submit results of ASVspoofing challenge [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=590].
* Write book -- Done.
||
* Deep speaker embedding.
|-

|-
|Zhiyuan Tang
||
* explore sub-questions,[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=595 baselines]
* poster for ICASSP17
||
* continue exploring sub-questions
|-

|}

-------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.2.20

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
|-

|-
|Yixiang Chen
||
* ASVspoofing challenge.
||
* ASVspoofing.
|-

|-
|Lantian Li
||
* Deep speaker embedding [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=591]
* ASVspoofing [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=590]
* Write book.
||
* ASVspoofing
|-

|-
|Zhiyuan Tang
||
* joint training of speech and language recognition, two languages for preliminary exploration,[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=595 baselines]
||
* explore sub-questions
|-

|}

文件:对Joint Training的一些可视化分析.pdf

2017-02-27T02:31:57Z

Luohang：

ASR Status Report 2017-2-13

2017-02-13T05:48:16Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.2.13

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
*
||
* Joint training of chinese and japanese
**To find whether joint training work on this database
|-

|-
|Ying Shi
||
* joint traing（speech spker）baseline and read some papers
||
* visualization joint training
**DNN same amount of label
|-

|-
|Yixiang Chen
||
*
||
* ASVspoofing
* Deep speaker embedding Two methods of improvement
|-

|-
|Lantian Li
||
* Deep speaker
* ASVspoofing
* Write book
||
* Deep speaker embedding：1、memory allocation，paramW sharing. 2、better than cosine distance while still worse than LDA and PLDA
* ASVspoofing：a text-dependent task
* Write book：complete chapter 1-3，leaving chapter 4.
|-

|-
|Zhiyuan Tang
||
* babel data preparation, [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=595 baselines]
||
* joint training of speech and language recognition, two languages for preliminary exploration
|-

|}

Asr-progress 2017.01

2017-01-13T06:32:16Z

Luohang：/* Daily Report */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="5"|2017.1.1
|Ying Shi || 1:30pm || 10:00pm || 8h30min || make new test set for kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.2
|Ying Shi || 1:30pm || 9:00pm || 7h30min || make new test set for kazak speech recognition and retrain TDNN　with fbank feature
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 10:00am || 6:30pm || 8.5h || revamp replay report
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.3
|Ying Shi ||9:10am || 10:00pm || 12h50min || 哈萨克语料的转换，完成了元音到前元音的转换，完成了代表序数的数字的转换（19- 代表第19），完成了代表范围的数字的转换（0-9 代表0到9 “-”前边的数字不同所写的‘-’的写法不同）
|-
|Hang luo || 1:00pm || 10:00pm || 9h || Finished latex version of joint training and mixlingual report
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:40am || 5:40pm || 8h ||
* Prepare for the Annual Meeting
* Take photos for members in CSLT
* Check book
|-
|-
| rowspan="5"|2017.1.4
|Ying Shi || || || ||
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Bi-monthly report and TRP check.
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am || 6:10pm || 7h10m ||
* Bi-monthly report
* Take and arrange photos
|-
|-
| rowspan="5"|2017.1.5
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am || 6:00pm|| ||
* Work on Dr.Wang's personal page.
|-
|-
| rowspan="5"|2017.1.6
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Modify TRP and ML book
|-
|Yixiang Chen ||9:30am || 9:00pm || 11.5h || coding cnn and pair-wise using tensorflow
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.7
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:30am || 7:30pm || 7h || recoding code
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am ||8:30pm || 11h||
* Write plan for Annual Meeting.
* Buy food and tools for Annual Meeting.
* Prepare presents box for Annual Meeting.
|-
|-
| rowspan="5"|2017.1.8
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am || 12:00am|| 2h||
* Revise the personal page.
|-
|-
| rowspan="5"|2017.1.9
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am ||15:00pm ||3h ||
* Revise the personal page.
* Putting photographs in order。
|-
|-
| rowspan="5"|2017.1.10
|Ying Shi || || || ||
|-
|Hang luo || 11:30am || 10:30pm || 11h || Prepare data for AP16-OL17 chinese ASR baseline
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || - ||- ||- ||-

|-
|-
| rowspan="5"|2017.1.11
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 9:00pm || 11.5h || Run chinese AM and prepare japanese data
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:45am || 5:45pm || 8h||
* Revise the personal page.
|-
|-
| rowspan="5"|2017.1.12
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Finished chinese baseline
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am ||6:00pm ||8h ||
* Revise the personal page.
* Help Jiyuan finish his questionnaires' making.
|-
|-
| rowspan="5"|2017.1.12
|Ying Shi || || || ||
|-
|Hang luo || 10:00am || 5:30pm || 7.5h || Run Japanese AM model
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||

Asr-progress 2017.01

2017-01-13T06:31:01Z

Luohang：/* Daily Report */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="5"|2017.1.1
|Ying Shi || 1:30pm || 10:00pm || 8h30min || make new test set for kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.2
|Ying Shi || 1:30pm || 9:00pm || 7h30min || make new test set for kazak speech recognition and retrain TDNN　with fbank feature
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 10:00am || 6:30pm || 8.5h || revamp replay report
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.3
|Ying Shi ||9:10am || 10:00pm || 12h50min || 哈萨克语料的转换，完成了元音到前元音的转换，完成了代表序数的数字的转换（19- 代表第19），完成了代表范围的数字的转换（0-9 代表0到9 “-”前边的数字不同所写的‘-’的写法不同）
|-
|Hang luo || 1:00pm || 10:00pm || 9h || Finished latex version of joint training and mixlingual report
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:40am || 5:40pm || 8h ||
* Prepare for the Annual Meeting
* Take photos for members in CSLT
* Check book
|-
|-
| rowspan="5"|2017.1.4
|Ying Shi || || || ||
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Bi-monthly report and TRP check.
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am || 6:10pm || 7h10m ||
* Bi-monthly report
* Take and arrange photos
|-
|-
| rowspan="5"|2017.1.5
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am || 6:00pm|| ||
* Work on Dr.Wang's personal page.
|-
|-
| rowspan="5"|2017.1.6
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Modify TRP and ML book
|-
|Yixiang Chen ||9:30am || 9:00pm || 11.5h || coding cnn and pair-wise using tensorflow
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.7
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:30am || 7:30pm || 7h || recoding code
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am ||8:30pm || 11h||
* Write plan for Annual Meeting.
* Buy food and tools for Annual Meeting.
* Prepare presents box for Annual Meeting.
|-
|-
| rowspan="5"|2017.1.8
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am || 12:00am|| 2h||
* Revise the personal page.
|-
|-
| rowspan="5"|2017.1.9
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am ||15:00pm ||3h ||
* Revise the personal page.
* Putting photographs in order。
|-
|-
| rowspan="5"|2017.1.10
|Ying Shi || || || ||
|-
|Hang luo || 11:30am || 10:30pm || 11h || Prepare data for AP16-OL17 chinese ASR baseline
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || - ||- ||- ||-

|-
|-
| rowspan="5"|2017.1.11
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 9:00pm || 11.5h || Run chinese AM and prepare japanese data
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:45am || 5:45pm || 8h||
* Revise the personal page.
|-
|-
| rowspan="5"|2017.1.12
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Finished chinese baseline
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am ||6:00pm ||8h ||
* Revise the personal page.
* Help Jiyuan finish his questionnaires' making.
| rowspan="5"|2017.1.12
|Ying Shi || || || ||
|-
|Hang luo || 10:00am || 5:30pm || 7.5h || Run Japanese AM model
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||

2017 Spring Festival

2017-01-12T08:05:48Z

Luohang：

{| class="wikitable"
!People !! start time !! end time
|-
|Jingyi Lin
||
2017.1.15
||
Haven't been decided.(I will be back to school at 2017.2.19)
|-

|-
|Yanqing Wang
||

||

|-

|-
|Hang Luo
||
2017.1.15
||
2017.2.9
|-

|-
|Ying Shi
||
2017.1.19
||
2017.2.5
|-

|-
|Yixiang Chen
||

||

|-

|-
|Lantian Li
||

||

|-

|-
|Zhiyuan Tang
||
2017.1.21
||
2017.2.5
|-

|}

Asr-progress 2017.01

2017-01-11T11:35:59Z

Luohang：/* Daily Report */

Asr-progress 2017.01

2017-01-11T11:35:24Z

Luohang：

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="5"|2017.1.1
|Ying Shi || 1:30pm || 10:00pm || 8h30min || make new test set for kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.2
|Ying Shi || 1:30pm || 9:00pm || 7h30min || make new test set for kazak speech recognition and retrain TDNN　with fbank feature
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 10:00am || 6:30pm || 8.5h || revamp replay report
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.3
|Ying Shi ||9:10am || 10:00pm || 12h50min || 哈萨克语料的转换，完成了元音到前元音的转换，完成了代表序数的数字的转换（19- 代表第19），完成了代表范围的数字的转换（0-9 代表0到9 “-”前边的数字不同所写的‘-’的写法不同）
|-
|Hang luo || 1:00pm || 10:00pm || 9h || Finished latex version of joint training and mixlingual report
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:40am || 5:40pm || 8h ||
* Prepare for the Annual Meeting
* Take photos for members in CSLT
* Check book
|-
|-
| rowspan="5"|2017.1.4
|Ying Shi || || || ||
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Bi-monthly report and TRP check.
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am || 6:10pm || 7h10m ||
* Bi-monthly report
* Take and arrange photos
|-
|-
| rowspan="5"|2017.1.5
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am || 6:00pm|| ||
* Work on Dr.Wang's personal page.
|-
|-
| rowspan="5"|2017.1.6
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Modify TRP and ML book
|-
|Yixiang Chen ||9:30am || 9:00pm || 11.5h || coding cnn and pair-wise using tensorflow
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2017.1.7
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:30am || 7:30pm || 7h || recoding code
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am ||8:30pm || 11h||
* Write plan for Annual Meeting.
* Buy food and tools for Annual Meeting.
* Prepare presents box for Annual Meeting.
|-
|-
| rowspan="5"|2017.1.8
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am || 12:00am|| 2h||
* Revise the personal page.
|-
|-
| rowspan="5"|2017.1.9
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 11:00am ||15:00pm ||3h ||
* Revise the personal page.
* Putting photographs in order。
|-
|-
| rowspan="5"|2017.1.10
|Ying Shi || || || ||
|-
|Hang luo || 1:30am || 10:30pm || 11h || Prepare data for AP16-OL17 chinese ASR baseline
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || - ||- ||- ||-

|-
|-
| rowspan="5"|2017.1.11
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 9:00pm || 11.5h || Run chinese AM and prepare japanese data
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:45am || 5:45pm || 8h||
* Revise the personal page.

ASR Status Report 2017-1-10

2017-01-10T06:11:34Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.1.10

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
* TRP and book checked.
||
* Train Japanese ASR baseline
|-

|-
|Ying Shi
||
* kazak speech recognition version1.0
* lexicon about Arabic numerals and loan words
||
* try to make language model by roots and affixes
|-

|-
|Yixiang Chen
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
|-

|}

---------------------------------------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2017.1.3

|Jingyi Lin
||
* Modify and supply Dr.Wang's personal page.
* Prepare for the Annual Meeting.
* Check CSLT books.(2,5)
||
* Check CSLT books.
|-

|-
|Yanqing Wang
||
* finish demo of distraction task
** choose subject / SVM type & train model in data sender: [[媒体文件:dataSender.png|data sender]]
** check the status of driver in data analyzer: [[媒体文件:dataAna1.png|focused]] [[媒体文件:dataAna2.png|distracted]]
* write a document on the mechanism of the program of both the data sender and data analyzer '''[delivery]'''
||
*
|-

|-
|Hang Luo
||
* TRP for joint training '''[delivery]'''
* Make a review of mix-lingual
||
*
|-

|-
|Ying Shi
||
* TRP for kazak speech recognition '''[delivery]'''
* make new test set which have lower ppl on LM
* The characteristics of the Kazak Language summarized by nurpolat [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/88/%E5%93%88%E8%90%A8%E5%85%8B%E8%AF%AD%E8%A8%80%E7%89%B9%E7%82%B9.pdf here]
||
* new kazak AM and LM
|-

|-
|Yixiang Chen
||
* Prepare the thesis proposal
* Integrate CNN + max-margin.
||
* Integrate CNN + max-margin.
|-

|-
|Lantian Li
||
* Deep speaker embedding
* Write book of robustness SRE.
* Wechat open account -- Hole.
* Replay detection on INTERSPEECH chanllenge -- Get the database.
||
* Deep speaker embedding.
* Write book.
* Replay detection on INTERSPEECH chanllenge.
|-

|-
|Zhiyuan Tang
||
* TRP of "How to Config Kaldi nnet3 (in Chinese)", describe the usage of 34 components '''[delivery]''';
* additional notes on "Multi-task Recurrent Model for True Multilingual Speech Recognition";
* Generative models, part of Chapter Deep Learning.
||
* check and submit the above 3 writings.
|-

|}

Asr-progress 2017.01

2017-01-06T09:12:55Z

Luohang：/* Daily Report */

Asr-progress 2016.12

2017-01-04T09:51:02Z

Luohang：/* Daily Report */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="4"|2016.12.1
|Ying Shi || 9:30am || 9:30pm || 12h || share two paper one about activation function one about visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 11:00am || 8:30pm || 9h30min || According to the weighted filter replay test
|-
|Yanqing Wang || 9:00am || 6:00pm || 9h || finish GUI of One-class SVM in Visual Studio
|-

|-
| rowspan="4"|2016.12.2
|Ying Shi || 9:40am || 9:30pm || 11h50min || some work for Chao Xing (Run dnn data from Chao Xing)
|-
|Hang luo || || || ||
|-
|Yixiang Chen ||9:30am || 7:30pm || 10h || fitting warping function
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.3
|Ying Shi || 2:00pm || 8:00pm || 6h || dnn model for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || 11:00am || 5:00pm || 6h || learn about DNN
|-

|-
| rowspan="4"|2016.12.4
|Ying Shi || || || || work at home for kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12am || 9:30pm || 9h30min || fitting warping function and use piecewise function for warping
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.5
|Ying Shi || 9:30am || 9:30pm || 12h || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 8:00pm || 11h30min || replay test(warping Select filter spectrum distribution)
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.6
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.7
|Ying Shi || 9:30am || 9:30pm || 12h || paper about activation function
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 5:30pm || 8h || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.8
|Ying Shi || 9:50am || 9:30pm || 11h40min || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.9
|Ying Shi || 9:40am || 9:40pm || 12h || some work for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 9h || coding for ole result
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.10
|Ying Shi || 9:00am || 9:40pm || 12h40min || corpus check with Amanjiao introduced by askar
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:00am || 9:30pm || 9h30min || statistical data
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.11
|Ying Shi || 9:30am || 9:50pm || 12h20min || work at home for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.12
|Ying Shi || 9:30am || 10:00pm || 12h30min || study how to make a spider to crawl data from the internet
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.13
|Ying Shi || 10:00am || 10:pm || 12h || kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.14
|Ying Shi || 10:00am || 10:30pm || 12h：30min || learn how to use scrapy to crawl data from the kazak website Uhhhh....... our IP may be prohibited by http://www.elarna.com/tote.php
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || coding cnn use tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.15
|Ying Shi || 9:30am || 9:30pm || 12h || spider for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.16
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="4"|2016.12.17
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.18
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="5"|2016.12.19
|Ying Shi || 9:30am || 8:30pm || 11h || some work for new kazak speech am
|-
|Hang luo || 9:40am || 6:40pm || 9h || Analysis decode result and find some decode error.
|-
|Yixiang Chen || 9:30am || 9:00pm || 11.5h || coding pair-wise
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 6:20pm || 9h || Check Chapter 1 in cslt.book: There are 14 mistakes and this chapter has not been finished.
|-
|-
| rowspan="5"|2016.12.20
|Ying Shi || 9:40am || 5:50pm || 8h10min || data prepare for new kazak speech AM;spider for kazak LM
|-
|Hang luo || 9：30am || 6:00pm || 8.5h || Prepare for writing joint training document.
|-
|Yixiang Chen || 9:30am || 6:00pm || 8.5h || write i-vector handbook
|-
|Yanqing Wang ||10:00am ||6:00pm || 8h || Make data sender and data Analyzer in my program communicate via socket
|-
|Jingyi Lin || 11:30am || 5:50pm || 6h20m ||
* Prepare for the annual meeting.
* Check Chapter 2 in cslt.book.

|-
| rowspan="5"|2016.12.21
|Ying Shi || 11:00am || 10:00pm || 10h || data preparation done for new kazak AM ,Maybe the ppl of kazak LM can be reduce below to 1000 so we need more corpus the new spider will be done tomorrow
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Know joint training process steps
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || revamp i-vector handbook
|-
|Yanqing Wang || || || || (work at home) Implement two-class-SVM in my program
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Learn how to design a web.
|-
|-
| rowspan="5"|2016.12.22
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 10:00pm || 12.5h || ReRun joint training and write respective documents.
|-
|Yixiang Chen ||1:00am || 8:00pm || 7h || deal with data
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 7:30pm ||10h ||
* Design personal web for Dr.Wang.
* Prepare for the annual meeting.
|-
|-
| rowspan="5"|2016.12.23
|Ying Shi || 9:30am || 10:00pm || 12h30min || New kazak speech AM and decode the rest is also poor(44.5%) maybe we need new test set
|-
|Hang luo || 9:30am|| 9:30pm || 12h || ReRun joint training
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Make the web.
* Prepare the Barbecue tools and beverage.
|-
|-
| rowspan="5"|2016.12.24
|Ying Shi || 1:30pm || 10:00pm || 8h30min || Technical report
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.25
|Ying Shi || 1:30pm || 7:00pm || 5h30min || Techical report,Kazak statue report
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.26
|Ying Shi || 9:40am|| 10:00pm|| 12h20min ||TRP in english
|-
|Hang luo || 1:30pm || 6:30pm || 5h || write joint training documents
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.27
|Ying Shi || 10:am || 10:pm || 12h || TRP in english will be translate to chinese
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.28
|Ying Shi || 9:40am || 9:20pm || 11h40min || TRP in chinese done
|-
|Hang luo || 12:00am || 10:00pm || 10h || cvss check ml book and finished joint training documents
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:40am || 18:00 || 8h20m ||
* Make Dr.Wang's personal web page.
* Do something about the CSLT's 2016 Photos.
* Draw pictures for vivi logo.
|-
|-
| rowspan="5"|2016.12.29
|Ying Shi ||9:30am||9:30pm || 12h || kazak decode by phone
|-
|Hang luo || 9:30am || 7:30pm || 10h || Read mixlingual papers
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am || 7:40pm ||9h40m ||
* Take photos of members in CSLT.
* Write essays for Dr Wang's personal web page.
|-
|-
| rowspan="5"|2016.12.30
|Ying Shi || 9:30am || 9:00pm || 11h30min || corpus check and sample
|-
|Hang luo ||9:30am|| 1:30pm || 4h || Read mixlingual papers
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am || 6:00pm || 8h||
* Take photos of members in CSLT.
* Check CSLT.BOOK.
* Choose presents for Annual Meeting.

|}

Asr-progress 2017.01

2017-01-04T09:43:32Z

Luohang：

Bi-monthly-2016-12-speech Speech group

2017-01-04T03:29:15Z

Luohang：

Team [ ]

Lantian Li [ ]

Yixiang Chen [ ]

Ying Shi [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/58/Bi-monthly_report_20170104_shiying.pdf]

Hang Luo [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/39/Bi-monthly_work_report_Luohang_20170104.pdf ]

Jingyi Lin [ ]

Yanqing Wang [ ]

Bi-monthly-2016-12-speech Speech group

2017-01-04T03:28:45Z

Luohang：

Team [ ]

Lantian Li [ ]

Yixiang Chen [ ]

Ying Shi [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/58/Bi-monthly_report_20170104_shiying.pdf]

Hang Luo [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Bi-monthly_work_report_Luohang_20170104.pdf ]

Jingyi Lin [ ]

Yanqing Wang [ ]

文件:Bi-monthly work report Luohang 20170104.pdf

2017-01-04T03:28:16Z

Luohang：

Asr-progress 2017.01

2017-01-04T02:55:12Z

Luohang：

ASR Status Report 2017-1-3

2017-01-03T07:18:29Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.26

|Jingyi Lin
||
* Modify and supply Dr.Wang's personal page.
* Prepare for the Annual Meeting.
* Check CSLT books.(2,5)
||
* Check CSLT books.
|-

|-
|Yanqing Wang
||
* finish demo of distraction task
** choose subject / SVM type & train model in data sender: [[媒体文件:dataSender.png|data sender]]
** check the status of driver in data analyzer: [[媒体文件:dataAna1.png|focused]] [[媒体文件:dataAna2.png|distracted]]
* write a document on the mechanism of the program of both the data sender and data analyzer
||
*
|-

|-
|Hang Luo
||
* TRP for joint training
* Make a review of mix-lingual
||
*
|-

|-
|Ying Shi
||
* TRP for kazak speech recognition
* make new test set which have lower ppl on LM
* The characteristics of the Kazak Language summarized by nurpolat [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/88/%E5%93%88%E8%90%A8%E5%85%8B%E8%AF%AD%E8%A8%80%E7%89%B9%E7%82%B9.pdf here]
||
* new kazak AM and LM
|-

|-
|Yixiang Chen
||
* Prepare the thesis proposal
* Integrate CNN + max-margin.
||
* Integrate CNN + max-margin.
|-

|-
|Lantian Li
||
* Deep speaker embedding
* Write book of robustness SRE.
* Wechat open account -- Hole.
* Replay detection on INTERSPEECH chanllenge -- Get the database.
||
* Deep speaker embedding.
* Write book.
* Replay detection on INTERSPEECH chanllenge.
|-

|-
|Zhiyuan Tang
||
* TRP of "How to Config Kaldi nnet3 (in Chinese)", describe the usage of 34 components;
* additional notes on "Multi-task Recurrent Model for True Multilingual Speech Recognition";
* Generative models, part of Chapter Deep Learning.
||
* check and submit the above 3 writings.
|-

|}

---------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.26

|Jingyi Lin
||
* Learn and make Dr.Wang's personal web page.
* Prepare for the CSLT's Annual Meeting.
||
* Finish Dr.Wang's personal web page.
* Take photos for menmbers in CSLT.
|-

|-
|Yanqing Wang
||
* implement the detection mechanism by socket
* find best parameters to avoid over-fitting
* add two-class-SVM to the program
* make GUI more pretty and easy to use
* improve the program's robustness
* screenshot:
** [[媒体文件:dataSender.png|data sender]]
**[[媒体文件:dataAnalyser.png|data analyzer]]
||
* write a document on the program
|-

|-
|Hang Luo
||
* Run joint training and write systemic script and documents
||
* Finish joint training documents
* Conclude joint training experiments result
* Make a review on mixlingual
|-

|-
|Ying Shi
||
* crawl corpus from internet.(I don't know whether the corpus is right or not.......)
* make new LM(complete)
* train new AM(complete)
* a part of TRP
||
* finish the TRP
|-

|-
|Yixiang Chen
||
* Prepare the input of speech data (trick of block segmentation)
* Complete the init version on max-margin SRE.
* Write TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明".
||
* Prepare the thesis proposal.
* Integrate CNN + max-margin.
|-

|-
|Lantian Li
||
* Deep speaker embedding
** Prepare two datasets and make the i-vector baselines.
* Write TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明".
* Write book of robustness SRE.
* Wechat open account.
||
* Deep speaker embedding.
* Write book.
* Replay detection on INTERSPEECH chanllenge.
|-

|-
|Zhiyuan Tang
||
* TRP of "How to Config Kaldi nnet3 (in Chinese)", not finished yet;
* outline of TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition";
* Generative models, part of Chapter Deep Learning.
||
* Finish the above 3 writings.
|-

|}

ASR Status Report 2017-1-3

2017-01-03T06:31:10Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.26

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
* TRP for joint training
* Make a review of mix-lingual
||
* Make a conclude for aurora4 and thchs30 joint training
|-

|-
|Ying Shi
||
* TRP for kazak speech recognition
* make new test set which have lower ppl on LM
* The characteristics of the Kazak Language summarized by nurpolat
||
* new kazak AM and LM
|-

|-
|Yixiang Chen
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* TRP of "How to Config Kaldi nnet3 (in Chinese)", describe the usage of 34 components;
* additional notes on "Multi-task Recurrent Model for True Multilingual Speech Recognition";
* Generative models, part of Chapter Deep Learning.
||
* check and submit the above 3 writings.
|-

|}

---------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.26

|Jingyi Lin
||
* Learn and make Dr.Wang's personal web page.
* Prepare for the CSLT's Annual Meeting.
||
* Finish Dr.Wang's personal web page.
* Take photos for menmbers in CSLT.
|-

|-
|Yanqing Wang
||
* implement the detection mechanism by socket
* find best parameters to avoid over-fitting
* add two-class-SVM to the program
* make GUI more pretty and easy to use
* improve the program's robustness
* screenshot:
** [[媒体文件:dataSender.png|data sender]]
**[[媒体文件:dataAnalyser.png|data analyzer]]
||
* write a document on the program
|-

|-
|Hang Luo
||
* Run joint training and write systemic script and documents
||
* Finish joint training documents
* Conclude joint training experiments result
* Make a review on mixlingual
|-

|-
|Ying Shi
||
* crawl corpus from internet.(I don't know whether the corpus is right or not.......)
* make new LM(complete)
* train new AM(complete)
* a part of TRP
||
* finish the TRP
|-

|-
|Yixiang Chen
||
* Prepare the input of speech data (trick of block segmentation)
* Complete the init version on max-margin SRE.
* Write TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明".
||
* Prepare the thesis proposal.
* Integrate CNN + max-margin.
|-

|-
|Lantian Li
||
* Deep speaker embedding
** Prepare two datasets and make the i-vector baselines.
* Write TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明".
* Write book of robustness SRE.
* Wechat open account.
||
* Deep speaker embedding.
* Write book.
* Replay detection on INTERSPEECH chanllenge.
|-

|-
|Zhiyuan Tang
||
* TRP of "How to Config Kaldi nnet3 (in Chinese)", not finished yet;
* outline of TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition";
* Generative models, part of Chapter Deep Learning.
||
* Finish the above 3 writings.
|-

|}

Asr-progress 2016.12

2016-12-29T10:59:22Z

Luohang：/* Daily Report */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="4"|2016.12.1
|Ying Shi || 9:30am || 9:30pm || 12h || share two paper one about activation function one about visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 11:00am || 8:30pm || 9h30min || According to the weighted filter replay test
|-
|Yanqing Wang || 9:00am || 6:00pm || 9h || finish GUI of One-class SVM in Visual Studio
|-

|-
| rowspan="4"|2016.12.2
|Ying Shi || 9:40am || 9:30pm || 11h50min || some work for Chao Xing (Run dnn data from Chao Xing)
|-
|Hang luo || || || ||
|-
|Yixiang Chen ||9:30am || 7:30pm || 10h || fitting warping function
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.3
|Ying Shi || 2:00pm || 8:00pm || 6h || dnn model for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || 11:00am || 5:00pm || 6h || learn about DNN
|-

|-
| rowspan="4"|2016.12.4
|Ying Shi || || || || work at home for kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12am || 9:30pm || 9h30min || fitting warping function and use piecewise function for warping
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.5
|Ying Shi || 9:30am || 9:30pm || 12h || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 8:00pm || 11h30min || replay test(warping Select filter spectrum distribution)
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.6
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.7
|Ying Shi || 9:30am || 9:30pm || 12h || paper about activation function
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 5:30pm || 8h || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.8
|Ying Shi || 9:50am || 9:30pm || 11h40min || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.9
|Ying Shi || 9:40am || 9:40pm || 12h || some work for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 9h || coding for ole result
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.10
|Ying Shi || 9:00am || 9:40pm || 12h40min || corpus check with Amanjiao introduced by askar
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:00am || 9:30pm || 9h30min || statistical data
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.11
|Ying Shi || 9:30am || 9:50pm || 12h20min || work at home for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.12
|Ying Shi || 9:30am || 10:00pm || 12h30min || study how to make a spider to crawl data from the internet
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.13
|Ying Shi || 10:00am || 10:pm || 12h || kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.14
|Ying Shi || 10:00am || 10:30pm || 12h：30min || learn how to use scrapy to crawl data from the kazak website Uhhhh....... our IP may be prohibited by http://www.elarna.com/tote.php
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || coding cnn use tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.15
|Ying Shi || 9:30am || 9:30pm || 12h || spider for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.16
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="4"|2016.12.17
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.18
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="5"|2016.12.19
|Ying Shi || 9:30am || 8:30pm || 11h || some work for new kazak speech am
|-
|Hang luo || 9:40am || 6:40pm || 9h || Analysis decode result and find some decode error.
|-
|Yixiang Chen || 9:30am || 9:00pm || 11.5h || coding pair-wise
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 6:20pm || 9h || Check Chapter 1 in cslt.book: There are 14 mistakes and this chapter has not been finished.
|-
|-
| rowspan="5"|2016.12.20
|Ying Shi || 9:40am || 5:50pm || 8h10min || data prepare for new kazak speech AM;spider for kazak LM
|-
|Hang luo || 9：30am || 6:00pm || 8.5h || Prepare for writing joint training document.
|-
|Yixiang Chen || 9:30am || 6:00pm || 8.5h || write i-vector handbook
|-
|Yanqing Wang ||10:00am ||6:00pm || 8h || Make data sender and data Analyzer in my program communicate via socket
|-
|Jingyi Lin || 11:30am || 5:50pm || 6h20m ||
* Prepare for the annual meeting.
* Check Chapter 2 in cslt.book.

|-
| rowspan="5"|2016.12.21
|Ying Shi || 11:00am || 10:00pm || 10h || data preparation done for new kazak AM ,Maybe the ppl of kazak LM can be reduce below to 1000 so we need more corpus the new spider will be done tomorrow
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Know joint training process steps
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || revamp i-vector handbook
|-
|Yanqing Wang || || || || (work at home) Implement two-class-SVM in my program
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Learn how to design a web.
|-
|-
| rowspan="5"|2016.12.22
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 10:00pm || 12.5h || ReRun joint training and write respective documents.
|-
|Yixiang Chen ||1:00am || 8:00pm || 7h || deal with data
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 7:30pm ||10h ||
* Design personal web for Dr.Wang.
* Prepare for the annual meeting.
|-
|-
| rowspan="5"|2016.12.23
|Ying Shi || 9:30am || 10:00pm || 12h30min || New kazak speech AM and decode the rest is also poor(44.5%) maybe we need new test set
|-
|Hang luo || 9:30am|| 9:30pm || 12h || ReRun joint training
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Make the web.
* Prepare the Barbecue tools and beverage.
|-
|-
| rowspan="5"|2016.12.24
|Ying Shi || 1:30pm || 10:00pm || 8h30min || Technical report
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.25
|Ying Shi || 1:30pm || 7:00pm || 5h30min || Techical report,Kazak statue report
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.26
|Ying Shi || 9:40am|| 10:00pm|| 12h20min ||TRP in english
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.27
|Ying Shi || 10:am || 10:pm || 12h || TRP in english will be translate to chinese
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.28
|Ying Shi || 9:40am || 9:20pm || 11h40min || TRP in chinese done
|-
|Hang luo || 12:00am || 10:00pm || 10h || cvss check ml book and finished joint training documents
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:40am || 18:00 || 8h20m ||
* Make Dr.Wang's personal web page.
* Do something about the CSLT's 2016 Photos.
* Draw pictures for vivi logo.
|-
|-
| rowspan="5"|2016.12.29
|Ying Shi |||| || ||
|-
|Hang luo || 9:30am || 7:30pm || 10h || Read mixlingual papers
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 10:00am || 7:40pm ||9h40m ||
* Take photos of members in CSLT.
* Write essays for Dr Wang's personal web page.

|}

Asr-progress 2016.12

2016-12-28T12:38:34Z

Luohang：/* Daily Report */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="4"|2016.12.1
|Ying Shi || 9:30am || 9:30pm || 12h || share two paper one about activation function one about visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 11:00am || 8:30pm || 9h30min || According to the weighted filter replay test
|-
|Yanqing Wang || 9:00am || 6:00pm || 9h || finish GUI of One-class SVM in Visual Studio
|-

|-
| rowspan="4"|2016.12.2
|Ying Shi || 9:40am || 9:30pm || 11h50min || some work for Chao Xing (Run dnn data from Chao Xing)
|-
|Hang luo || || || ||
|-
|Yixiang Chen ||9:30am || 7:30pm || 10h || fitting warping function
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.3
|Ying Shi || 2:00pm || 8:00pm || 6h || dnn model for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || 11:00am || 5:00pm || 6h || learn about DNN
|-

|-
| rowspan="4"|2016.12.4
|Ying Shi || || || || work at home for kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12am || 9:30pm || 9h30min || fitting warping function and use piecewise function for warping
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.5
|Ying Shi || 9:30am || 9:30pm || 12h || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 8:00pm || 11h30min || replay test(warping Select filter spectrum distribution)
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.6
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.7
|Ying Shi || 9:30am || 9:30pm || 12h || paper about activation function
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 5:30pm || 8h || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.8
|Ying Shi || 9:50am || 9:30pm || 11h40min || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.9
|Ying Shi || 9:40am || 9:40pm || 12h || some work for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 9h || coding for ole result
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.10
|Ying Shi || 9:00am || 9:40pm || 12h40min || corpus check with Amanjiao introduced by askar
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:00am || 9:30pm || 9h30min || statistical data
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.11
|Ying Shi || 9:30am || 9:50pm || 12h20min || work at home for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.12
|Ying Shi || 9:30am || 10:00pm || 12h30min || study how to make a spider to crawl data from the internet
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.13
|Ying Shi || 10:00am || 10:pm || 12h || kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.14
|Ying Shi || 10:00am || 10:30pm || 12h：30min || learn how to use scrapy to crawl data from the kazak website Uhhhh....... our IP may be prohibited by http://www.elarna.com/tote.php
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || coding cnn use tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.15
|Ying Shi || 9:30am || 9:30pm || 12h || spider for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.16
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="4"|2016.12.17
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.18
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="5"|2016.12.19
|Ying Shi || 9:30am || 8:30pm || 11h || some work for new kazak speech am
|-
|Hang luo || 9:40am || 6:40pm || 9h || Analysis decode result and find some decode error.
|-
|Yixiang Chen || 9:30am || 9:00pm || 11.5h || coding pair-wise
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 6:20pm || 9h || Check Chapter 1 in cslt.book: There are 14 mistakes and this chapter has not been finished.
|-
|-
| rowspan="5"|2016.12.20
|Ying Shi || 9:40am || 5:50pm || 8h10min || data prepare for new kazak speech AM;spider for kazak LM
|-
|Hang luo || 9：30am || 6:00pm || 8.5h || Prepare for writing joint training document.
|-
|Yixiang Chen || 9:30am || 6:00pm || 8.5h || write i-vector handbook
|-
|Yanqing Wang ||10:00am ||6:00pm || 8h || Make data sender and data Analyzer in my program communicate via socket
|-
|Jingyi Lin || 11:30am || 5:50pm || 6h20m ||
* Prepare for the annual meeting.
* Check Chapter 2 in cslt.book.

|-
| rowspan="5"|2016.12.21
|Ying Shi || 11:00am || 10:00pm || 10h || data preparation done for new kazak AM ,Maybe the ppl of kazak LM can be reduce below to 1000 so we need more corpus the new spider will be done tomorrow
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Know joint training process steps
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || revamp i-vector handbook
|-
|Yanqing Wang || || || || (work at home) Implement two-class-SVM in my program
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Learn how to design a web.
|-
|-
| rowspan="5"|2016.12.22
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 10:00pm || 12.5h || ReRun joint training and write respective documents.
|-
|Yixiang Chen ||1:00am || 8:00pm || 7h || deal with data
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 7:30pm ||10h ||
* Design personal web for Dr.Wang.
* Prepare for the annual meeting.
|-
|-
| rowspan="5"|2016.12.23
|Ying Shi || 9:30am || 10:00pm || 12h30min || New kazak speech AM and decode the rest is also poor(44.5%) maybe we need new test set
|-
|Hang luo || 9:30am|| 9:30pm || 12h || ReRun joint training
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Make the web.
* Prepare the Barbecue tools and beverage.
|-
|-
| rowspan="5"|2016.12.24
|Ying Shi || 1:30pm || 10:00pm || 8h30min || Technical report
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.25
|Ying Shi || 1:30pm || 7:00pm || 5h30min || Techical report,Kazak statue report
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.26
|Ying Shi || 9:40am|| 10:00pm|| 12h20min ||TRP in english
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.27
|Ying Shi || 10:am || 10:pm || 12h || TRP in english will be translate to chinese
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||
|-
|-
| rowspan="5"|2016.12.28
|Ying Shi || || || ||
|-
|Hang luo || 12:00am || 10:00pm || 10h || cvss check ml book and finished joint training documents
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:40am || 18:00 || 8h20m ||
* Make Dr.Wang's personal web page.
* Do something about the CSLT's 2016 Photos.
* Draw pictures for vivi logo.

|}

ASR Status Report 2016-12-26

2016-12-26T05:54:02Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.26

|Jingyi Lin
||
* Learn and make Dr.Wang's personal web page.
* Prepare for the CSLT's Annual Meeting.
||
* Finish Dr.Wang's personal web page.
* Take photos for menmbers in CSLT.
|-

|-
|Yanqing Wang
||
* implement the detection mechanism by socket
* find best parameters to avoid over-fitting
* add two-class-SVM to the program
* make GUI more pretty and easy to use
* improve the program's robustness
* screenshot:
** [[媒体文件:dataSender.png|data sender]]
**[[媒体文件:dataAnalyser.png|data analyzer]]
||
* write a document on the program
|-

|-
|Hang Luo
||
* Run joint training and write systemic script and documents
||
* Finish joint training documents
* Conclude joint training experiments result
* Make a review on mixlingual
|-

|-
|Ying Shi
||
* crawl corpus from internet.(I don't know whether the corpus is right or not.......)
* make new LM(complete)
* train new AM(complete)
* a part of TRP
||
* finish the TRP
|-

|-
|Yixiang Chen
||
* Prepare the input of speech data (trick of block segmentation)
* Complete the init version on max-margin SRE.
* Write TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明".
||
* Prepare the thesis proposal.
* Integrate CNN + max-margin.
|-

|-
|Lantian Li
||
* Deep speaker embedding
** Prepare two datasets and make the i-vector baselines.
* Write TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明".
* Write book of robustness SRE.
* Wechat open account.
||
* Deep speaker embedding.
* Write book.
* Replay detection on INTERSPEECH chanllenge.
|-

|-
|Zhiyuan Tang
||
* TRP of "How to Config Kaldi nnet3 (in Chinese)", not finished yet;
* outline of TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition".
||
* Finish the above 2 TRPs.
|-

|}

-------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.19

|Jingyi Lin
||
* --
||
* Concentrate on checking the cslt.book.
* Prepare for the annual convention.
|-

|-
|Yanqing Wang
||
* build a data sender ( read & generate txt files of distracted feature )
* build a data analyzer ( detect the modification of files and make response ( show tokens ) )
* screenshot:
**[[媒体文件:GUI_distracted.png|distraction]]
**[[媒体文件:GUI_focus.png|focus]]
||
* (maybe) replace the detection mechanism by socket
* find best parameters to avoid over-fitting
* add two-class SVM to the program
* make GUI more pretty and easy to use
|-

|-
|Hang Luo
||
* Compare decode result between mono and bi LM, and the decode result ues bi LM before and after joint
* Choose wrong decode sentence and find its difference between baseline and shareGMM baseline
* Finished ML book
||
* Continue joint training analysis work, but I'm very confused about how to improve
|-

|-
|Ying Shi
||
* some work about kazak lm
* crawl data from kazak internet
||
* run new AM by current speech data
* get more corpus from internet
* use current corpus make LM and decode
|-

|-
|Yixiang Chen
||
* Leanring tensorflow
* coding pair wise net use tensorflow
* alter CNN
||
* coding CNN connect pair wise
* Dealing with the issue of different lengths of voice
|-

|-
|Lantian Li
||
* LRE challenge on AP16-OL7.
* Jeju for APSIPA16.
||
* LRE on AP16-OL7.
* Deep speaker embedding.
|-

|-
|Zhiyuan Tang
||
* Jeju for APSIPA16.
||
* A speech about recent ASR improvements.
* A supplementary TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition".
|-

|}

Asr-progress 2016.12

2016-12-26T05:41:47Z

Luohang：

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="4"|2016.12.1
|Ying Shi || 9:30am || 9:30pm || 12h || share two paper one about activation function one about visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 11:00am || 8:30pm || 9h30min || According to the weighted filter replay test
|-
|Yanqing Wang || 9:00am || 6:00pm || 9h || finish GUI of One-class SVM in Visual Studio
|-

|-
| rowspan="4"|2016.12.2
|Ying Shi || 9:40am || 9:30pm || 11h50min || some work for Chao Xing (Run dnn data from Chao Xing)
|-
|Hang luo || || || ||
|-
|Yixiang Chen ||9:30am || 7:30pm || 10h || fitting warping function
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.3
|Ying Shi || 2:00pm || 8:00pm || 6h || dnn model for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || 11:00am || 5:00pm || 6h || learn about DNN
|-

|-
| rowspan="4"|2016.12.4
|Ying Shi || || || || work at home for kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12am || 9:30pm || 9h30min || fitting warping function and use piecewise function for warping
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.5
|Ying Shi || 9:30am || 9:30pm || 12h || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 8:00pm || 11h30min || replay test(warping Select filter spectrum distribution)
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.6
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.7
|Ying Shi || 9:30am || 9:30pm || 12h || paper about activation function
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 5:30pm || 8h || write replay report
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.8
|Ying Shi || 9:50am || 9:30pm || 11h40min || work for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10min || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.9
|Ying Shi || 9:40am || 9:40pm || 12h || some work for Chao Xing
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 9h || coding for ole result
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.10
|Ying Shi || 9:00am || 9:40pm || 12h40min || corpus check with Amanjiao introduced by askar
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:00am || 9:30pm || 9h30min || statistical data
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.11
|Ying Shi || 9:30am || 9:50pm || 12h20min || work at home for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.12
|Ying Shi || 9:30am || 10:00pm || 12h30min || study how to make a spider to crawl data from the internet
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.13
|Ying Shi || 10:00am || 10:pm || 12h || kazak LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || learning tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.14
|Ying Shi || 10:00am || 10:30pm || 12h：30min || learn how to use scrapy to crawl data from the kazak website Uhhhh....... our IP may be prohibited by http://www.elarna.com/tote.php
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 6:30pm || 8h || coding cnn use tensorflow
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.15
|Ying Shi || 9:30am || 9:30pm || 12h || spider for kazak lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.16
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="4"|2016.12.17
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.12.18
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|-
| rowspan="5"|2016.12.19
|Ying Shi || 9:30am || 8:30pm || 11h || some work for new kazak speech am
|-
|Hang luo || 9:40am || 6:40pm || 9h || Analysis decode result and find some decode error.
|-
|Yixiang Chen || 9:30am || 9:00pm || 11.5h || coding pair-wise
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 6:20pm || 9h || Check Chapter 1 in cslt.book: There are 14 mistakes and this chapter has not been finished.
|-
|-
| rowspan="5"|2016.12.20
|Ying Shi || 9:40am || 5:50pm || 8h10min || data prepare for new kazak speech AM;spider for kazak LM
|-
|Hang luo || 9：30am || 6:00pm || 8.5h || Prepare for writing joint training document.
|-
|Yixiang Chen || 9:30am || 6:00pm || 8.5h || write i-vector handbook
|-
|Yanqing Wang ||10:00am ||6:00pm || 8h || Make data sender and data Analyzer in my program communicate via socket
|-
|Jingyi Lin || 11:30am || 5:50pm || 6h20m ||
* Prepare for the annual meeting.
* Check Chapter 2 in cslt.book.

|-
| rowspan="5"|2016.12.21
|Ying Shi || 11:00am || 10:00pm || 10h || data preparation done for new kazak AM ,Maybe the ppl of kazak LM can be reduce below to 1000 so we need more corpus the new spider will be done tomorrow
|-
|Hang luo || 10:00am || 6:30pm || 8.5h || Know joint training process steps
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || revamp i-vector handbook
|-
|Yanqing Wang || || || || (work at home) Implement two-class-SVM in my program
|-
|Jingyi Lin || 9:30am || 8:00pm || 10h30m ||
* Learn how to design a web.
|-
|-
| rowspan="5"|2016.12.22
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 10:00pm || 12.5h || ReRun joint training and write respective documents.
|-
|Yixiang Chen ||1:00am || 8:00pm || 7h || deal with data
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:20am || 7:30pm ||10h ||
* Design personal web for Dr.Wang.
* Prepare for the annual meeting.
|-
|-
| rowspan="5"|2016.12.23
|Ying Shi || 9:30am || 10:00pm || 12h30min || New kazak speech AM and decode the rest is also poor(44.5%) maybe we need new test set
|-
|Hang luo || 9:30am|| 9:30pm || 12h || ReRun joint training
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || 9:30am || || ||
* Make the web.
* Prepare the Barbecue tools and beverage.
|-
| rowspan="5"|2016.12.24
|Ying Shi || 1:30pm || 10:00pm || 8h30min || Technical report
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||

|-
| rowspan="5"|2016.12.25
|Ying Shi || 1:30pm || 7:00pm || 5h30min || Techical report,Kazak statue report
|-
|Hang luo || |||| ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-
|Jingyi Lin || || || ||

|}

Asr-progress 2016.12

2016-12-22T13:05:28Z

Luohang：/* Daily Report */

Asr-progress 2016.12

2016-12-22T06:30:25Z

Luohang：/* Daily Report */

Asr-progress 2016.12

2016-12-21T01:30:37Z

Luohang：/* Daily Report */

Asr-progress 2016.12

2016-12-19T09:26:35Z

Luohang：/* Daily Report */

ASR Status Report 2016-12-19

2016-12-19T06:09:57Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.19

|Jingyi Lin
||
*
||
* Concentrate on checking the cslt.book.
* Prepare for the annual convention.
|-

|-
|Yanqing Wang
||
* build a data sender ( read & generate txt files of distracted feature )
||
* build a data analyzer ( detect the modification of files and make response ( show tokens ) )
|-

|-
|Hang Luo
||
* Compare decode result between mono and bi LM, and the decode result ues bi LM before and after joint
* Choose wrong decode sentence and find its difference between baseline and shareGMM baseline
* Finished ML book
||
* Continue joint training analysis work, but I'm very confused about how to improve
|-

|-
|Ying Shi
||
* some work about kazak lm
* crawl data from kazak internet
||
* run new AM by current speech data
* get more corpus from internet
* use current corpus make LM and decode
|-

|-
|Yixiang Chen
||
* Leanring tensorflow
* coding pair wise net use tensorflow
* alter CNN
||
* coding CNN connect pair wise
* Dealing with the issue of different lengths of voice
|-

|-
|Lantian Li
||
* LRE challenge on AP16-OL7.
* Jeju for APSIPA16.
||
* LRE on AP16-OL7.
* Deep speaker embedding.
|-

|-
|Zhiyuan Tang
||
* Jeju for APSIPA16.
||
* A speech about recent ASR improvements.
* A supplementary TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition".
|-

|}

-------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.12.12

|Yanqing Wang
||
* read a paper about driving distraction detection task
||
* show normal/distraction patterns of a driver with one class and two class SVM
|-

|-
|Hang Luo
||
* Compared mono-language model and bi-language model decode result.
* Read paper of WFST.
||
* Use different corpus or generate mix-lingual corpus to run experiments
|-

|-
|Ying Shi
||
* work from Chao Xing down
* kazak lm
** got some corpus from a student who study in Minzu University of China.But the corpus is short (about 10000) so the ppl is also poor.
** spider
||
* kazak lm
|-

|-
|Yixiang Chen
||
* Complete the replay task experiment and report
||
* learning tensorflow coding DNN and CNN net
|-

|-
|Lantian Li
||
* interim report done;
* PPT for APSIPA16;
* LRE challenge on AP16-OL7.
* Deep speaker embedding restart!
* Submit TRP-20160011 on Replay detection.
||
* Jeju for APSIPA16.
|-

|-
|Zhiyuan Tang
||
* interim report done;
* PPT for APSIPA16;
* language mask[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]
||
* Jeju for APSIPA16.
|-

|}

ASR Status Report 2016-12-19

2016-12-19T06:08:54Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.19

|Jingyi Lin
||
*
||
* Concentrate on checking the cslt.book.
* Prepare for the annual convention.
|-

|-
|Yanqing Wang
||
* build a data sender ( read & generate txt files of distracted feature )
||
* build a data analyzer ( detect the modification of files and make response ( show tokens ) )
|-

|-
|Hang Luo
||
* Continue joint training analysis work, but I'm very confused about how to improve
||
* Compare decode result between mono and bi LM, and the decode result ues bi LM before and after joint
* Choose wrong decode sentence and find its difference between baseline and shareGMM baseline
* Finished ML book
|-

|-
|Ying Shi
||
* some work about kazak lm
* crawl data from kazak internet
||
* run new AM by current speech data
* get more corpus from internet
* use current corpus make LM and decode
|-

|-
|Yixiang Chen
||
* Leanring tensorflow
* coding pair wise net use tensorflow
* alter CNN
||
* coding CNN connect pair wise
* Dealing with the issue of different lengths of voice
|-

|-
|Lantian Li
||
* LRE challenge on AP16-OL7.
* Jeju for APSIPA16.
||
* LRE on AP16-OL7.
* Deep speaker embedding.
|-

|-
|Zhiyuan Tang
||
* Jeju for APSIPA16.
||
* A speech about recent ASR improvements.
* A supplementary TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition".
|-

|}

-------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.12.12

|Yanqing Wang
||
* read a paper about driving distraction detection task
||
* show normal/distraction patterns of a driver with one class and two class SVM
|-

|-
|Hang Luo
||
* Compared mono-language model and bi-language model decode result.
* Read paper of WFST.
||
* Use different corpus or generate mix-lingual corpus to run experiments
|-

|-
|Ying Shi
||
* work from Chao Xing down
* kazak lm
** got some corpus from a student who study in Minzu University of China.But the corpus is short (about 10000) so the ppl is also poor.
** spider
||
* kazak lm
|-

|-
|Yixiang Chen
||
* Complete the replay task experiment and report
||
* learning tensorflow coding DNN and CNN net
|-

|-
|Lantian Li
||
* interim report done;
* PPT for APSIPA16;
* LRE challenge on AP16-OL7.
* Deep speaker embedding restart!
* Submit TRP-20160011 on Replay detection.
||
* Jeju for APSIPA16.
|-

|-
|Zhiyuan Tang
||
* interim report done;
* PPT for APSIPA16;
* language mask[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]
||
* Jeju for APSIPA16.
|-

|}

ASR Status Report 2016-12-19

2016-12-19T06:00:15Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="7"|2016.12.19

|Jingyi Lin
||
*
||
*
|-

|-
|Yanqing Wang
||
*
||
*
|-

|-
|Hang Luo
||
* Continue joint training analysis work, but I'm very confused about how to improve
||
* Compare decode result between mono and bi LM
* Choose wrong decode sentence and find its difference between baseline and shareGMM baseline
* Finished ML book
|-

|-
|Ying Shi
||
* some work about kazak lm
* crawl data from kazak internet
||
* run new AM by current speech data
* get more corpus from internet
* use current corpus make LM and decode
|-

|-
|Yixiang Chen
||
* Leanring tensorflow
* coding pair wise net use tensorflow
* alter CNN
||
* coding CNN connect pair wise
* Dealing with the issue of different lengths of voice
|-

|-
|Lantian Li
||
* LRE challenge on AP16-OL7.
* Jeju for APSIPA16.
||
* LRE on AP16-OL7.
* Deep speaker embedding.
|-

|-
|Zhiyuan Tang
||
* Jeju for APSIPA16.
||
* A speech about recent ASR improvements.
* A supplementary TRP for "Multi-task Recurrent Model for True Multilingual Speech Recognition".
|-

|}

-------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.12.12

|Yanqing Wang
||
* read a paper about driving distraction detection task
||
* show normal/distraction patterns of a driver with one class and two class SVM
|-

|-
|Hang Luo
||
* Compared mono-language model and bi-language model decode result.
* Read paper of WFST.
||
* Use different corpus or generate mix-lingual corpus to run experiments
|-

|-
|Ying Shi
||
* work from Chao Xing down
* kazak lm
** got some corpus from a student who study in Minzu University of China.But the corpus is short (about 10000) so the ppl is also poor.
** spider
||
* kazak lm
|-

|-
|Yixiang Chen
||
* Complete the replay task experiment and report
||
* learning tensorflow coding DNN and CNN net
|-

|-
|Lantian Li
||
* interim report done;
* PPT for APSIPA16;
* LRE challenge on AP16-OL7.
* Deep speaker embedding restart!
* Submit TRP-20160011 on Replay detection.
||
* Jeju for APSIPA16.
|-

|-
|Zhiyuan Tang
||
* interim report done;
* PPT for APSIPA16;
* language mask[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]
||
* Jeju for APSIPA16.
|-

|}

ASR Status Report 2016-12-12

2016-12-12T12:35:54Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.12.12

|Yanqing Wang
||
* read a paper about driving distraction detection task
||
* show normal/distraction patterns of a driver with one class and two class SVM
|-

|-
|Hang Luo
||
* Compared mono-language model and bi-language model decode result.
* Read paper of WFST.
||
* Use different corpus or generate mix-lingual corpus to run experiments
|-

|-
|Ying Shi
||
* work from Chao Xing down
* kazak lm
** got some corpus from a student who study in Minzu University of China.But the corpus is short (about 10000) so the ppl is also poor.
** spider
||
* kazak lm
|-

|-
|Yixiang Chen
||
* Complete the replay task experiment and report
||
* learning tensorflow coding DNN and CNN net
|-

|-
|Lantian Li
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* interim report done;
* PPT for APSIPA16;
* language mask[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]
||
* Jeju for APSIPA16.
|-

|}

------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.11.28

|Yanqing Wang
||
* finish building GUI of one-class-SVM in Visual Studio
**[[媒体文件:One-class SVM.png|screenShot]]
* learn about deep learning
||
* process data with the GUI of one-class-SVM
|-

|-
|Hang Luo
||
* Experiments about fixed language model, find language information almost has no improve in ASR so far
* share one paper
* Experiments on smaller language model,128 cells still has great result
||
* Try different language model or other direction
* Paper about joint training
|-

|-
|Ying Shi
||
* some work about kazak LM
* DNN for Chao Xing
* ml-book check to cvs
* share two papers
||
* some work about kazak lm(try to reduce the ppl)
* paper about activation function
* DNN for Chao Xing
|-

|-
|Yixiang Chen
||
* According to the weighted filter replay test
* fitting warping function and use piecewise function for warping
||
* complete replay test
* learning tensorfloat
|-

|-
|Lantian Li
||
* LRE on AP16-OL7. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** The deep model still can not beat the i-vector model.
* Emotion challenge in CCPR. --> Done.
* Replay detection. --> Done.
* Phd forum. --> Done
||
* LRE task.
* Write replay detection technical report.
* oral PPT for APSIPA 2016.
|-

|-
|Zhiyuan Tang
||
* materials for PhD Dissertations,
* materials for paper accepted by TASLP;
* language mask[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]
||
* scans the TASLP paper for several times,
* oral PPT for APSIPA 2016.
|-

|}

ASR Status Report 2016-12-05

2016-12-05T07:10:23Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.11.28

|Yanqing Wang
||
* finish building GUI of one-class-SVM in Visual Studio
**[[媒体文件:One-class SVM.png|screenShot]]
* learn about deep learning
||
* process data with the GUI of one-class-SVM
|-

|-
|Hang Luo
||
* Experiments about fixed language model, find language information almost has no improve in ASR so far
* share one paper
* Experiments on smaller language model,128 cells still has great result
||
* Try different language model or other direction
* Paper about joint training
|-

|-
|Ying Shi
||
* some work about kazak LM
* DNN for Chao Xing
* ml-book check to cvs
* share two papers
||
* some work about kazak lm(try to reduce the ppl)
* paper about activation function
* DNN for Chao Xing
|-

|-
|Yixiang Chen
||
* According to the weighted filter replay test
* fitting warping function and use piecewise function for warping
||
* complete replay test
* learning tensorfloat
|-

|-
|Lantian Li
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* materials for PhD Dissertations,
* materials for paper accepted by TASLP;
* language mask
||
* scans the TASLP paper for several times,
* oral PPT for APSIPA 2016.
|-

|}
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.11.28

|Yanqing Wang
||
* fighting with building GUI interface of one-class-SVM in Visual Studio but not finished yet
** configure LibSVM toolkit in Visual Studio
** implement the basic functions of LibSVM in Visual Studio
** learn to create Qt project using Visual Studio and Qt Creator
||
* finish building GUI interface of one-class-SVM in Visual Studio
* make the GUI interface display dynamically with the change of given data
|-

|-
|Hang Luo
||
* Do experiments about joint learning including:
** Fixed language model and give its information to speech model
** Try smaller language model and find its result
* Inter Speech paper talk about multi-task and highway connection
||
* Continue to do experiments and read paper about language recognition model
|-

|-
|Ying Shi
||
* some work about kazak speech recognition
* cnn visualization
* paper reading
* ML-book done
* DNN with different activation function (Sigmoid Tanh Relu pnorm)
||
* cnn visualization
|-

|-
|Yixiang Chen
||
* Continue replay detection (Freq-Weighting and Mel-Weighting).
* Pooling replay data for UBM training
||
* Continue replay detection (Change data set and Warping)
|-

|-
|Lantian Li
||
* LRE on AP16-OL7. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** 'StatisticsComponent'
** The effect of Vad / Padding.
* Replay detection.
** performance-driven based Freq-Weighting
||
* LRE task.
* Freq-Warping and CNN-training.
|-

|-
|Zhiyuan Tang
||
* A speech named 'Deep Learning in Speech Recognition' in Chengdu;
* Decoding with language mask seems helpless, not concluded.
||
* use language mask in a proper way.
* prepare materials for paper accepted by TASLP.
|-

|}

Cslt-member-visitors

2016-12-04T13:25:07Z

Luohang：/* Hang Luo (罗航) */

==Professionals==

===Maoning Wang (王卯宁）===
[[文件:Daisy.jpg|200px]]
* Centeral Fiance and Economic University
* 2016.9-
* Finance processing

===Caixia Wang (王彩霞）===
[[文件:Daisy.jpg|200px]]
* University of diplomatic
* 2016.9-
* Finance processing

=== Yang Feng (冯洋) ===
[[文件:Fengyang.jpg| 200px]]
* 2016.6.21-
* Huilan Ltd
* language processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
[[文件:Daisy.jpg|200px]]
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
[[文件:Zhangjiyuan.png|200px]]
* PKU
* 2016.4-
* neural generation model
* [[媒体文件:An overview of machine translation.pptx|Bi-weekly report]]
* [[媒体文件:Zhangjy_data.jpg|Data_security_agreement]]

===Jingyi Lin(林婧伊)===
[[文件:JinyiLin_photo.jpg|200px]]
* China chemical university
* 2016.4.12-
* Speech processing
* [[媒体文件:Bi_weekly_report_linjy.ppt|Bi-weekly report]]
*[[媒体文件:DataSecurityAgreement_JingyiLin.jpg|DataSecurityAgreement]]

===Ziwei Bai (白子薇）===
[[文件:Ziwei Bai.jpg|200px]]
* BUPT
* 2016.5-
* QA
* [[媒体文件:xxx|Bi-weekly report]]

===Ying Shi (石颖）===
[[文件:Ying_shi.jpg|200px]]
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]
*[[媒体文件:DataSecurityAgreement_YingShi.jpg|DataSecurityAgreement]]

===Aodong Li (李傲冬）===
[[文件:李傲冬.jpg|200px]]
* BUPT
* 2016.6-
* Neural generation model
* [[媒体文件:Biweekly_report_aodong.pptx|Bi-weekly report]]

===Yixiang Chen (陈怿翔)===
[[文件:Chenyx.jpg|200px]]
*University of China Mining
* 2016.7-
* Speech processing
* [[媒体文件:Chenyx_report.pdf |Bi-weekly report]]
* [[媒体文件:Chenyx data.jpg|Data_security_agreement]]

===Shiyue Zhang(张诗悦)===
[[文件:Zhang Shiyue.jpg|200px]]
* BUTP
* 2016.9.06-
* Language processing
* [[媒体文件:xxx|Bi-weekly report]]

===Andy Zhang(张安迪)===
[[文件:andyzhang.jpg|200px]]
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
[[文件:罗航.png|200px]]
* PKU
* 2016.10-
* Speech processing
* [[媒体文件:Bi-weekly_work_report_Luohang.pptx|Bi-weekly report]]
* [[媒体文件:Security.jpg|Data_security_agreement]]

===Bin Fu (符宾）===
[[文件:Fubin.jpg|200px]]
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
[[文件:guli.jpg|200px]]
* Xingjiang U.
* 2016.11-
* Translation
*[[媒体文件:3.jpg|Data_security_agreement]]

===Yanqing Wang（王延清）===
[[文件:wyq photo.jpeg|200px]]
* BUPT
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]
*[[媒体文件:DataSecurityAgreement wangyanqing.jpg|Data_security_agreement]]

===Peilun Xiao（肖培伦）===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.12-
* NLP
* [[媒体文件:xxx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
[[文件:weiy_photo.jpg|200px]]
* 2016.10 -
* Speech processing

文件:Security.jpg

2016-12-04T13:21:55Z

Luohang：

ASR Status Report 2016-11-28

2016-12-01T01:08:20Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.11.28

|Yanqing Wang
||
* fighting with building GUI interface of one-class-SVM in Visual Studio but not finished yet
** configure LibSVM toolkit in Visual Studio
** implement the basic functions of LibSVM in Visual Studio
** learn to create Qt project using Visual Studio and Qt Creator
||
* finish building GUI interface of one-class-SVM in Visual Studio
* make the GUI interface display dynamically with the change of given data
|-

|-
|Hang Luo
||
* Do experiments about joint learning including:
** Fixed language model and give its information to speech model
** Try smaller language model and find its result
* Inter Speech paper talk about multi-task and highway connection
||
* Continue to do experiments and read paper about language recognition model
|-

|-
|Ying Shi
||
* some work about kazak speech recognition
* cnn visualization
* paper reading
* ML-book done
* DNN with different activation function (Sigmoid Tanh Relu pnorm)
||
* cnn visualization
|-

|-
|Yixiang Chen
||
* Continue replay detection (Freq-Weighting and Mel-Weighting).
* Pooling replay data for UBM training
||
* Continue replay detection (Change data set and Warping)
|-

|-
|Lantian Li
||
* LRE on AP16-OL7. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** 'StatisticsComponent'
** The effect of Vad / Padding.
* Replay detection.
** performance-driven based Freq-Weighting
||
* LRE task.
* Freq-Warping and CNN-training.
|-

|-
|Zhiyuan Tang
||
* A speech named 'Deep Learning in Speech Recognition' in Chengdu;
* Decoding with language mask seems helpless, not concluded.
||
* use language mask in a proper way.
* prepare materials for paper accepted by TASLP.
|-

|}
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.11.21
|Hang Luo
||
* Explore the language recognition models including:
* Evaluate the model in the aspect of sentence and frame, find the accuracy is very high.
* Minimize the language model, train it single and joint with speech model, evaluate its result.
||
* Continue doing the basic explore of joint training.
* Read paper about multi-language recognition models and others.
|-

|-
|Ying Shi
||
* fighting with kazak speech recognition system:because the huge size of HCLG.fst the decoding job always make the sever done.
There are several method I have tried
* change the size or word list and corpus this method not worked very well
* prune the LM .And the parameter been used to prune the LM is 2e-7 the size of LM reduce from 290M to 60M but the result about wer is very poor
* I have upload some result about several experiment to CVSS[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=576]
||
* there are too much private affairs about myself so the job about visualization last week has been delayed I will try my best to finish it the week

|-
|Yixiang Chen
||
* Learn MFCC extraction mechanism.
* Read kaldi computer-feature code and find how to change MFCC.
* Frequency-weighting based feature extraction.
||
* Continue replay detection (Freq-Weighting and Freq-Warping).
|-

|-
|Lantian Li
||
* Joint-training on SRE and LRE (LRE task). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** Tdnn is better than LSTM.
** LRE is a long-term task.
* Briefly overview Interspeech SRE-related papers.
* CSLT-Replay detection.
** Baseline done (Freq / Mel domain).
** performance-driven based Freq-Weighting and Freq-Warping --> Yixiang.
||
* LRE task.
* Replay detection.
|-

|-
|Zhiyuan Tang
||
* report for Weekly Reading (a brief review of interspeech16), just prepared;
* language scores as decoding mask (1.multiply probability, very bad; 2.add log-softmax, a little bad)
* training with mask failed
||
* training with shared layers;
* explore single tasks.
|}

ASR Status Report 2016-11-28

2016-12-01T01:07:52Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="6"|2016.11.28

|Yanqing Wang
||
* fighting with building GUI interface of one-class-SVM in Visual Studio but not finished yet
** configure LibSVM toolkit in Visual Studio
** implement the basic functions of LibSVM in Visual Studio
** learn to create Qt project using Visual Studio and Qt Creator
||
* finish building GUI interface of one-class-SVM in Visual Studio
* make the GUI interface display dynamically with the change of given data
|-

|-
|Hang Luo
||
* Do experiments about joint learning including:
** Fixed language model and give its information to speech model
** Try smaller language model and find its result
* Inter Speech paper talk about multi-task and highway connection
||
* Continue do experiments and read paper about language recognition model
|-

|-
|Ying Shi
||
* some work about kazak speech recognition
* cnn visualization
* paper reading
* ML-book done
* DNN with different activation function (Sigmoid Tanh Relu pnorm)
||
* cnn visualization
|-

|-
|Yixiang Chen
||
* Continue replay detection (Freq-Weighting and Mel-Weighting).
* Pooling replay data for UBM training
||
* Continue replay detection (Change data set and Warping)
|-

|-
|Lantian Li
||
* LRE on AP16-OL7. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** 'StatisticsComponent'
** The effect of Vad / Padding.
* Replay detection.
** performance-driven based Freq-Weighting
||
* LRE task.
* Freq-Warping and CNN-training.
|-

|-
|Zhiyuan Tang
||
* A speech named 'Deep Learning in Speech Recognition' in Chengdu;
* Decoding with language mask seems helpless, not concluded.
||
* use language mask in a proper way.
* prepare materials for paper accepted by TASLP.
|-

|}
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.11.21
|Hang Luo
||
* Explore the language recognition models including:
* Evaluate the model in the aspect of sentence and frame, find the accuracy is very high.
* Minimize the language model, train it single and joint with speech model, evaluate its result.
||
* Continue doing the basic explore of joint training.
* Read paper about multi-language recognition models and others.
|-

|-
|Ying Shi
||
* fighting with kazak speech recognition system:because the huge size of HCLG.fst the decoding job always make the sever done.
There are several method I have tried
* change the size or word list and corpus this method not worked very well
* prune the LM .And the parameter been used to prune the LM is 2e-7 the size of LM reduce from 290M to 60M but the result about wer is very poor
* I have upload some result about several experiment to CVSS[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=576]
||
* there are too much private affairs about myself so the job about visualization last week has been delayed I will try my best to finish it the week

|-
|Yixiang Chen
||
* Learn MFCC extraction mechanism.
* Read kaldi computer-feature code and find how to change MFCC.
* Frequency-weighting based feature extraction.
||
* Continue replay detection (Freq-Weighting and Freq-Warping).
|-

|-
|Lantian Li
||
* Joint-training on SRE and LRE (LRE task). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** Tdnn is better than LSTM.
** LRE is a long-term task.
* Briefly overview Interspeech SRE-related papers.
* CSLT-Replay detection.
** Baseline done (Freq / Mel domain).
** performance-driven based Freq-Weighting and Freq-Warping --> Yixiang.
||
* LRE task.
* Replay detection.
|-

|-
|Zhiyuan Tang
||
* report for Weekly Reading (a brief review of interspeech16), just prepared;
* language scores as decoding mask (1.multiply probability, very bad; 2.add log-softmax, a little bad)
* training with mask failed
||
* training with shared layers;
* explore single tasks.
|}

Cslt-member-visitors

2016-11-30T08:43:03Z

Luohang：/* Hang Luo (罗航) */

==Professionals==

===Maoning Wang (王卯宁）===
[[文件:Daisy.jpg|200px]]
* Centeral Fiance and Economic University
* 2016.9-
* Finance processing

===Caixia Wang (王彩霞）===
[[文件:Daisy.jpg|200px]]
* University of diplomatic
* 2016.9-
* Finance processing

=== Yang Feng (冯洋) ===
[[文件:Fengyang.jpg| 200px]]
* 2016.6.21-
* Huilan Ltd
* language processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
[[文件:Daisy.jpg|200px]]
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
[[文件:Daisy.jpg|200px]]
* PKU
* 2016.4-
* neural generation model
* [[媒体文件:xxx|Bi-weekly report]]

===Jingyi Lin(林婧伊)===
[[文件:Daisy.jpg|200px]]
* China chemical university
* 2016.4.12-
* Speech processing
* [[媒体文件:xxx|Bi-weekly report]]

===Ziwei Bai (白紫薇）===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.5-
* QA
* [[媒体文件:xxx|Bi-weekly report]]

===Ying Shi (石颖）===
[[文件:Daisy.jpg|200px]]
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]

===Aodong Li (李傲冬）===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.6-
* Neural generation model
* [[媒体文件:xxx|Bi-weekly report]]

===Yixiang Chen (陈怿翔)===
[[文件:Daisy.jpg|200px]]
*University of China Mining
* 2016.7-
* Speech processing
* [[媒体文件:xxx|Bi-weekly report]]

===Shiyue Zhang(张诗悦)===
[[文件:Daisy.jpg|200px]]
* BUTP
* 2016.9.06-
* Language processing
* [[媒体文件:xxx|Bi-weekly report]]

===Andy Zhang(张安迪)===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
[[文件:罗航.png|200px]]
* PKU
* 2016.10-
* Speech processing
* [[媒体文件:Bi-weekly_work_report_Luohang.pptx|Bi-weekly report]]

===Bin Fu (符宾）===
[[文件:Daisy.jpg|200px]]
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
[[文件:Daisy.jpg|200px]]
* Xingjiang U.
* 2016.11-
* Translation

===Yanqing Wang（王延清）===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]

===Peilun Xiao（肖培伦）===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.12-
* NLP
* [[媒体文件:xxx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
[[文件:Daisy.jpg|200px]]
* 2016.10 -
* Speech processing

文件:罗航.png

2016-11-30T08:42:07Z

Luohang：

Asr-progress 2016.11

2016-11-30T07:25:34Z

Luohang：

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="4"|2016.11.1
|Ying Shi || 10:00am || 8:30pm || 8h || ML-book
|-
|Hang luo || 9:30am || 7:30pm || 10h || Related work about joint training
|-
|Yixiang Chen || 10:00am || 8:30pm || 8h30min || ML-book
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.2
|Ying Shi || 9:20am || 9:30pm || 12h10min || bimonthly report ;paper
|-
|Hang luo || 9:40am || 7:20pm || 9h40min || bimonthly report, Read Inter Speech paper
|-
|Yixiang Chen || 9:30am || 7:30pm || 9h30min || bimonthly report,check PPT
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.3
|Ying Shi || 9:20am || 9:30pm || 12h10min || check worklist for zhiyong zhang
|-
|Hang luo || 9:30am || 9:30pm || 12h || paper reading report
|-
|Yixiang Chen || 10:00am || 10:30pm || 12h30min || check worklist ,data processing
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.4
|Ying Shi || 9:30am || 9:30am || 12h || kazak speech recognition
|-
|Hang luo || 10:30am || 6:30pm || 8h || lexicon checking
|-
|Yixiang Chen || || || || Exam Review
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.5
|Ying Shi || 1:30pm || 9:30pm || 8h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.6
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.7
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 7:30pm || 10h || Read paper about DNN highway connection
|-
|Yixiang Chen || || || || Exam
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.8
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 11:30am || 7:30am || 8h || Get Know to multi-task and read papers
|-
|Yixiang Chen || 9:30am || 5:30am || 8h || read paper and MLbook
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.9
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 8:30pm || 11h || Read multi-task paper, but there are many confuses.
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.10
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Think about new direction of joint training
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.11
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 3:30pm || 6h || Read adversirial joint training paper
|-
|Yixiang Chen || 9:30am || 7:00pm || 9h30min || MLbook
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.12
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 1:00pm || 7:30pm || 6h30min || learing MFCC
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.13
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.14
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition AM down some work about decode
|-
|Hang luo || 9:30am || 7:30pm || 10h || Know language model and ready for experiments
|-
|Yixiang Chen || 9:30am || 10:00pm || 12h30min || replay test ready
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.15
|Ying Shi || 9:30pm || 9:30pm || 12h || prepare LM for kazak speech recongition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || finish MLbook chapter 7
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.16
|Ying Shi || 9:30pm || 9:30pm || 12h || some work about HCLG.fst
|-
|Hang luo || 9:30am || 7:30pm || 10h || Read Inter Speech paper
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || processing data for replay
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.17
|Ying Shi || 9:30pm || 9:30pm || 12h ||4 experiment for kazak decoding the result is poor maybe we need new corpus for lm
|-
|Hang luo || 9:30pm || 7:30am || 10h || Try simple language model and find its accuracy
|-
|Yixiang Chen || 9:30pm || 7:30pm || 10h || dividing frequency band test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.18
|Ying Shi || 9:30pm || 9:30pm || 12h || some work about kazak speech recognition LM
|-
|Hang luo || 9:30am || 7:30pm || 10h || Fixed LRE model and do experiments
|-
|Yixiang Chen || 12:30am || 7:30pm || 7h || dividing Mel frequency band test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.19
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:30am || 7：30pm || 7h || change weight on Frequency and replay test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.21
|Ying Shi || 2:30pm || 6:00pm || 3.5h || check corpus with teacher SAMAHAN
|-
|Hang luo || 9:30pm || 6:30am || 9h || Read LRE code and modify configuration
|-
|Yixiang Chen || 9:30am || 8:00pm || 10h30min || Complete the comparison of Frequency and Mel
|-
|Yanqing Wang || 9:00 pm || 10:30 pm || 13h30min || Learn to use Qt Creator
|-

|-
| rowspan="4"|2016.11.22
|Ying Shi || 9:30 || 9:30 || 12h || paper about visualization
|-
|Hang luo || 9:30am || 6:30pm || 9h || Run the changed model
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || To prepare UBM database,join replay data
|-
|Yanqing Wang || 9:00am || 8:00pm || 11h || learn to create Qt project in Visual Studio and Qt creator
|-

|-
| rowspan="4"|2016.11.23
|Ying Shi || 9:30 || 9:30 || 12h || data cleaning about kazak speech paper about visualization
|-
|Hang luo || 2:00pm || 7:00pm || 5h || Summay readed paper
|-
|Yixiang Chen ||9:30am || 8:30pm || 11h || To find the best configuration(num_bin) and the experiment
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.24
|Ying Shi || 9:30 || 9:30 || 12h || new dnn model with different activation function (Sigmod Tanh relu pnorm)
|-
|Hang luo || 9:30am || 6:30pm || 9h || Share 4 papers
|-
|Yixiang Chen || 9:30am || 8:30pm || 11h || To find the best configuration and the experiment
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.25
|Ying Shi || 9:30 || 6：00|| 8：30h || new dnn model with different activation function (Sigmod Tanh relu pnorm) and finish the ML book
|-
|Hang luo || 9:30am || 6:30pm || 9h || Continue doing experiments on fixed LRE model
|-
|Yixiang Chen ||9:30am || 8:30pm || 11h || Comparative experiments on linear and MEL effect
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.26
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.27
|Ying Shi || 11：00am || 8：50pm || || work at home some work about new dnn and cnn visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.28
|Ying Shi || 9:40am || 9:40pm || 12h || cnn visualization sparsity of network.There are too many point on the matlab figure so it can't be open,I will try another way.
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 5:30pm || 8h || dividing frequency band and compute EER of bank
|-
|Yanqing Wang || 9:00am || 11:00pm || 14h || continue to implement the LibSVM toolkit in Visual Studio
|-

|-
| rowspan="4"|2016.11.29
|Ying Shi || 9:30am || 9:00pm || 11h30m || the coming visulization job will focus on activation function so I read some paper about activation function(cnn sparsity will be finish in this week)
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h ||compare baseline and weight , warping test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.30
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|}

===Time Off Table===
{| class="wikitable"
! Name !! Days off
|-
|Ying Shi || 1+0.5
|-
|Hang luo || 0.5+1+0.5+2
|-
|Yixiang Chen|| 1+1+1+1
|-

|}

Asr-progress 2016.11

2016-11-30T07:12:27Z

Luohang：/* Time Off Table */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="4"|2016.11.1
|Ying Shi || 10:00am || 8:30pm || 8h || ML-book
|-
|Hang luo || 9:30am || 7:30pm || 10h || Related work about joint training
|-
|Yixiang Chen || 10:00am || 8:30pm || 8h30min || ML-book
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.2
|Ying Shi || 9:20am || 9:30pm || 12h10min || bimonthly report ;paper
|-
|Hang luo || 9:40am || 7:20pm || 9h40min || bimonthly report, Read Inter Speech paper
|-
|Yixiang Chen || 9:30am || 7:30pm || 9h30min || bimonthly report,check PPT
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.3
|Ying Shi || 9:20am || 9:30pm || 12h10min || check worklist for zhiyong zhang
|-
|Hang luo || 9:30am || 9:30pm || 12h || paper reading report
|-
|Yixiang Chen || 10:00am || 10:30pm || 12h30min || check worklist ,data processing
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.4
|Ying Shi || 9:30am || 9:30am || 12h || kazak speech recognition
|-
|Hang luo || 10:30am || 6:30pm || 8h || lexicon checking
|-
|Yixiang Chen || || || || Exam Review
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.5
|Ying Shi || 1:30pm || 9:30pm || 8h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.6
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.7
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 7:30pm || 10h || Read paper about DNN highway connection
|-
|Yixiang Chen || || || || Exam
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.8
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 11:30am || 7:30am || 8h || Get Know to multi-task and read papers
|-
|Yixiang Chen || 9:30am || 5:30am || 8h || read paper and MLbook
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.9
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 8:30pm || 11h || Read multi-task paper, but there are many confuses.
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.10
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Think about new direction of joint training
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.11
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 3:30pm || 6h || Read adversirial joint training paper
|-
|Yixiang Chen || 9:30am || 7:00pm || 9h30min || MLbook
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.12
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 1:00pm || 7:30pm || 6h30min || learing MFCC
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.13
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.14
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition AM down some work about decode
|-
|Hang luo || 9:30am || 7:30pm || 10h || Know language model and ready for experiments
|-
|Yixiang Chen || 9:30am || 10:00pm || 12h30min || replay test ready
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.15
|Ying Shi || 9:30pm || 9:30pm || 12h || prepare LM for kazak speech recongition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || finish MLbook chapter 7
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.16
|Ying Shi || 9:30pm || 9:30pm || 12h || some work about HCLG.fst
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || processing data for replay
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.17
|Ying Shi || 9:30pm || 9:30pm || 12h ||4 experiment for kazak decoding the result is poor maybe we need new corpus for lm
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30pm || 7:30pm || 10h || dividing frequency band test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.18
|Ying Shi || 9:30pm || 9:30pm || 12h || some work about kazak speech recognition LM
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:30am || 7:30pm || 7h || dividing Mel frequency band test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.19
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 12:30am || 7：30pm || 7h || change weight on Frequency and replay test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.21
|Ying Shi || 2:30pm || 6:00pm || 3.5h || check corpus with teacher SAMAHAN
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 8:00pm || 10h30min || Complete the comparison of Frequency and Mel
|-
|Yanqing Wang || 9:00 pm || 10:30 pm || 13h30min || Learn to use Qt Creator
|-

|-
| rowspan="4"|2016.11.22
|Ying Shi || 9:30 || 9:30 || 12h || paper about visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h || To prepare UBM database,join replay data
|-
|Yanqing Wang || 9:00am || 8:00pm || 11h || learn to create Qt project in Visual Studio and Qt creator
|-

|-
| rowspan="4"|2016.11.23
|Ying Shi || 9:30 || 9:30 || 12h || data cleaning about kazak speech paper about visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen ||9:30am || 8:30pm || 11h || To find the best configuration(num_bin) and the experiment
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.24
|Ying Shi || 9:30 || 9:30 || 12h || new dnn model with different activation function (Sigmod Tanh relu pnorm)
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 8:30pm || 11h || To find the best configuration and the experiment
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.25
|Ying Shi || 9:30 || 6：00|| 8：30h || new dnn model with different activation function (Sigmod Tanh relu pnorm) and finish the ML book
|-
|Hang luo || || || ||
|-
|Yixiang Chen ||9:30am || 8:30pm || 11h || Comparative experiments on linear and MEL effect
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.26
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.27
|Ying Shi || 11：00am || 8：50pm || || work at home some work about new dnn and cnn visualization
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.28
|Ying Shi || 9:40am || 9:40pm || 12h || cnn visualization sparsity of network.There are too many point on the matlab figure so it can't be open,I will try another way.
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 5:30pm || 8h || dividing frequency band and compute EER of bank
|-
|Yanqing Wang || 9:00am || 11:00pm || 14h || continue to implement the LibSVM toolkit in Visual Studio
|-

|-
| rowspan="4"|2016.11.29
|Ying Shi || 9:30am || 9:00pm || 11h30m || the coming visulization job will focus on activation function so I read some paper about activation function(cnn sparsity will be finish in this week)
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 9:30am || 7:30pm || 10h ||compare baseline and weight , warping test
|-
|Yanqing Wang || || || ||
|-

|-
| rowspan="4"|2016.11.30
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-
|Yanqing Wang || || || ||
|-

|}

===Time Off Table===
{| class="wikitable"
! Name !! Days off
|-
|Ying Shi || 1+0.5
|-
|Hang luo || 0.5+1+2
|-
|Yixiang Chen|| 1+1+1+1
|-

|}

Cslt-member-visitors

2016-11-30T02:05:14Z

Luohang：/* Hang Luo (罗航) */

==Professors==

===Maoning Wang (王卯宁）===
* University of Central Finance and Economic
* 2016.9-
* Finance processing

===Aodong Li (王彩霞）===
* University of diplomatic
* 2016.9-
* Finance processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
* PKU
* 2016.4-
* neural generation model

===Jingyi Lin(林婧伊)===
* China chemical university
* 2016.4.12-
* Speech processing

===Ziwei Bai (白紫薇）===
* BUPT
* 2016.5-
* QA

===Ying Shi (石颖）===
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]

===Aodong Li (李傲冬）===
* BUPT
* 2016.6-
* Neural generation model

===Yixiang Chen (陈怿翔)===
*University of China Mining
* 2016.7-
* Speech processing

===Shiyue Zhang(张诗悦)===
* BUTP
* 2016.9.06-
* Language processing

===Andy Zhang(张安迪)===
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
* PKU
* 2016.10-
* Speech processing
* [[媒体文件:Bi-weekly_work_report_Luohang.pptx|Bi-weekly report]]

===Bin Fu (符宾）===
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
* Xingjiang U.
* 2016.11-
* Translation

===Yanqing Wang（王延清）===
* Yanqing Wang
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
* 2016.10 -
* Speech processing

Cslt-member-visitors

2016-11-30T02:03:32Z

Luohang：/* Hang Luo (罗航) */

==Professors==

===Maoning Wang (王卯宁）===
* University of Central Finance and Economic
* 2016.9-
* Finance processing

===Aodong Li (王彩霞）===
* University of diplomatic
* 2016.9-
* Finance processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
* PKU
* 2016.4-
* neural generation model

===Jingyi Lin(林婧伊)===
* China chemical university
* 2016.4.12-
* Speech processing

===Ziwei Bai (白紫薇）===
* BUPT
* 2016.5-
* QA

===Ying Shi (石颖）===
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]

===Aodong Li (李傲冬）===
* BUPT
* 2016.6-
* Neural generation model

===Yixiang Chen (陈怿翔)===
*University of China Mining
* 2016.7-
* Speech processing

===Shiyue Zhang(张诗悦)===
* BUTP
* 2016.9.06-
* Language processing

===Andy Zhang(张安迪)===
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
* PKU
* 2016.10-
* Speech processing
* http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Bi-weekly_work_report_Luohang.pptx

===Bin Fu (符宾）===
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
* Xingjiang U.
* 2016.11-
* Translation

===Yanqing Wang（王延清）===
* Yanqing Wang
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
* 2016.10 -
* Speech processing

Cslt-member-visitors

2016-11-30T01:57:23Z

Luohang：/* Hang Luo (罗航) */

==Professors==

===Maoning Wang (王卯宁）===
* University of Central Finance and Economic
* 2016.9-
* Finance processing

===Aodong Li (王彩霞）===
* University of diplomatic
* 2016.9-
* Finance processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
* PKU
* 2016.4-
* neural generation model

===Jingyi Lin(林婧伊)===
* China chemical university
* 2016.4.12-
* Speech processing

===Ziwei Bai (白紫薇）===
* BUPT
* 2016.5-
* QA

===Ying Shi (石颖）===
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]

===Aodong Li (李傲冬）===
* BUPT
* 2016.6-
* Neural generation model

===Yixiang Chen (陈怿翔)===
*University of China Mining
* 2016.7-
* Speech processing

===Shiyue Zhang(张诗悦)===
* BUTP
* 2016.9.06-
* Language processing

===Andy Zhang(张安迪)===
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
* PKU
* 2016.10-
* Speech processing
*

===Bin Fu (符宾）===
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
* Xingjiang U.
* 2016.11-
* Translation

===Yanqing Wang（王延清）===
* Yanqing Wang
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
* 2016.10 -
* Speech processing

Cslt-member-visitors

2016-11-30T01:54:22Z

Luohang：/* Hang Luo (罗航) */

==Professors==

===Maoning Wang (王卯宁）===
* University of Central Finance and Economic
* 2016.9-
* Finance processing

===Aodong Li (王彩霞）===
* University of diplomatic
* 2016.9-
* Finance processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
* PKU
* 2016.4-
* neural generation model

===Jingyi Lin(林婧伊)===
* China chemical university
* 2016.4.12-
* Speech processing

===Ziwei Bai (白紫薇）===
* BUPT
* 2016.5-
* QA

===Ying Shi (石颖）===
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]

===Aodong Li (李傲冬）===
* BUPT
* 2016.6-
* Neural generation model

===Yixiang Chen (陈怿翔)===
*University of China Mining
* 2016.7-
* Speech processing

===Shiyue Zhang(张诗悦)===
* BUTP
* 2016.9.06-
* Language processing

===Andy Zhang(张安迪)===
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
* PKU
* 2016.10-
* Speech processing
* http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Bi-weekly_work_report_Luohang.pptx

===Bin Fu (符宾）===
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
* Xingjiang U.
* 2016.11-
* Translation

===Yanqing Wang（王延清）===
* Yanqing Wang
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
* 2016.10 -
* Speech processing

文件:Bi-weekly work report Luohang.pptx

2016-11-30T01:50:31Z

Luohang：

ASR Status Report 2016-11-21

2016-11-21T00:53:18Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week

|-
| rowspan="5"|2016.11.21
|Hang Luo
||
* Explore the language recognition models including:
* Evaluate the model in the aspect of sentence and frame, find the accuracy is very high.
* Minimize the language model, train it single and joint with speech model, evaluate its result.
||
* Continue doing the basic explore of joint training.
* Read paper about multi-language recognition models and others.
|-

|-
|Ying Shi
||
* fighting with kazak speech recognition system:because the huge size of HCLG.fst the decoding job always make the sever done.
There are several method I have tried
* change the size or word list and corpus this method not worked very well
* prune the LM .And the parameter been used to prune the LM is 2e-7 the size of LM reduce from 290M to 60M but the result about wer is very poor
* I have upload some result about several experiment to CVSS[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=576]
||
* there are too much private affairs about myself so the job about visualization last week has been delayed I will try my best to finish it the week

|-
|Yixiang Chen
||
* Learn MFCC extraction mechanism.
* Read kaldi computer-feature code and find how to change MFCC.
* Frequency-weighting based feature extraction.
||
* Continue replay detection (Freq-Weighting and Freq-Warping).
|-

|-
|Lantian Li
||
* Joint-training on SRE and LRE (LRE task). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
** Tdnn is better than LSTM.
** LRE is a long-term task.
* Briefly overview Interspeech SRE-related papers.
* CSLT-Replay detection.
** Baseline done (Freq / Mel domain).
** performance-driven based Freq-Weighting and Freq-Warping --> Yixiang.
||
* LRE task.
* Replay detection.
|-

|-
|Zhiyuan Tang
||
* report for Weekly Reading (a brief review of interspeech16), just prepared;
* language scores as decoding mask (1.multiply probability, very bad; 2.add log-softmax, a little bad)
* training with mask failed
||
* training with shared layers;
* explore single tasks.
|}

-----------------------------------------------------------------------------------------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week

|-
| rowspan="5"|2016.11.14
|Hang Luo
||
* read papers about highway connection and multi-task
||
* Explore the language recognition model on speech+language joint training, find how to use languange information.
* finish ML-book
|-

|-
|Ying Shi
||
* kazaka recognition baseline finished [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=576 here]
||
* figuie of ml-book read paper nn visualization
|-

|-
|Yixiang Chen
||
* Motify the ML-book and read paper.
* Prepare the replay detection baseline.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=571]
||
* Complete the replay baseline and attempt to modify MFCC calculation.
|-

|-
|Lantian Li
||
* Complete the Joint-training on TASLP (speaker parts). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=573]
* Joint-training on SRE and LRE (Still over-fitting !). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
* Read some papers and download four database. [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Data_resources]
* CSLT-Replay detection database is OK! [/work4/lilt/Replay]
||
* Joint-training on SRE and LRE.
* Baseline system on replay detection.
|-

|-
|Zhiyuan Tang
||
* finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].
* prepare a brief review of interspeech16.
||
* report for Weekly Reading (a brief review of interspeech16);
* joint training for bilingual: language scores as decoding mask, explore the best info receivier by studying single tasks with extra info.
|}

Asr-progress 2016.11

2016-11-17T07:55:14Z

Luohang：/* Time Off Table */

===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016.11.1
|Ying Shi || 10:00am || 8:30pm || 8h || ML-book
|-
|Hang luo || 9:30am || 7:30pm || 10h || Related work about joint training
|-
|Yixiang Chen || 10:00am || 8:30pm || 8h30min || ML-book
|-

|-
| rowspan="3"|2016.11.2
|Ying Shi || 9:20am || 9:30pm || 12h10min || bimonthly report ;paper
|-
|Hang luo || 9:40am || 7:20pm || 9h40min || bimonthly report, Read Inter Speech paper
|-
|Yixiang Chen || 9:30am || 7:30pm || 9h30min || bimonthly report,check PPT
|-

|-
| rowspan="3"|2016.11.3
|Ying Shi || 9:20am || 9:30pm || 12h10min || check worklist for zhiyong zhang
|-
|Hang luo || 9:30am || 9:30pm || 12h || paper reading report
|-
|Yixiang Chen || 10:00am || 10:30pm || 12h30min || check worklist ,data processing
|-

|-
| rowspan="3"|2016.11.4
|Ying Shi || 9:30am || 9:30am || 12h || kazak speech recognition
|-
|Hang luo || 10:30am || 6:30pm || 8h || lexicon checking
|-
|Yixiang Chen || || || || Exam Review
|-

|-
| rowspan="3"|2016.11.5
|Ying Shi || 1:30pm || 9:30pm || 8h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-

|-
| rowspan="3"|2016.11.6
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-

|-
| rowspan="3"|2016.11.7
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 7:30pm || 10h || Read paper about DNN highway connection
|-
|Yixiang Chen || || || || Exam
|-

|-
| rowspan="3"|2016.11.8
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 11:30am || 7:30am || 8h || Get Know to multi-task and read papers
|-
|Yixiang Chen || 9:30am || 5:30am || 8h || read paper and MLbook
|-

|-
| rowspan="3"|2016.11.9
|Ying Shi || 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 8:30pm || 11h || Read multi-task paper, but there are many confuses.
|-
|Yixiang Chen || || || ||
|-

|-
| rowspan="3"|2016.11.10
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 6:00pm || 8.5h || Think about new direction of joint training
|-
|Yixiang Chen || || || ||
|-

|-
| rowspan="3"|2016.11.11
|Ying Shi|| 9:30pm || 9:30pm || 12h || kazak speech recognition
|-
|Hang luo || 9:30am || 3:30pm || 6h || Read adversirial joint training paper
|-
|Yixiang Chen || 9:30am || 7:00pm || 9h30min || MLbook
|-

|-
| rowspan="3"|2016.11.12
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || 1:00pm || 7:30pm || 6h30min || learing MFCC
|-

|-
| rowspan="3"|2016.11.13
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-

|-
| rowspan="3"|2016.11.14
|Ying Shi || || || ||
|-
|Hang luo || 9:30am || 7:30pm || 10h || Know language model and ready for experiments
|-
|Yixiang Chen || 9:30am || 10:00pm || 12h30min || replay test ready
|-

|-
| rowspan="3"|2016.11.15
|Ying Shi || || || ||
|-
|Hang luo || || || ||
|-
|Yixiang Chen || || || ||
|-

|}

===Time Off Table===
{| class="wikitable"
! Name !! Days off
|-
|Ying Shi || 1
|-
|Hang luo || 0.5+1
|-
|Yixiang Chen|| 1+1+1+1
|-

|}

Asr-progress 2016.11

2016-11-17T07:54:39Z

Luohang：/* Daily Report */

ASR Status Report 2016-11-14

2016-11-17T07:47:38Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week

|-
| rowspan="5"|2016.11.14
|Hang Luo
||
* read papers about highway connection and multi-task
||
* Explore the language recognition model on speech+language joint training, find how to use languange information.
* finish ML-book
|-

|-
|Ying Shi
||
* kazaka recognition baseline finished [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=576 here]
||
* figuie of ml-book read paper nn visualization
|-

|-
|Yixiang Chen
||
* Motify the ML-book and read paper.
* Prepare the replay detection baseline.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=571]
||
* Complete the replay baseline and attempt to modify MFCC calculation.
|-

|-
|Lantian Li
||
* Complete the Joint-training on TASLP (speaker parts). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=573]
* Joint-training on SRE and LRE (Still over-fitting !). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
* Read some papers and download four database. [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Data_resources]
* CSLT-Replay detection database is OK! [/work4/lilt/Replay]
||
* Joint-training on SRE and LRE.
* Baseline system on replay detection.
|-

|-
|Zhiyuan Tang
||
* finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].
* prepare a brief review of interspeech16.
||
* report for Weekly Reading (a brief review of interspeech16);
* joint training for bilingual: language scores as decoding mask, explore the best info receivier by studying single tasks with extra info.
|}

-----------------------------------------------------------------------------------------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week

|-
| rowspan="5"|2016.11.07
|Hang Luo
||
* make a report of 2 Inter Speech papers
* run joint training experiments and the result is [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=luohang&step=view_request&cvssid=578]
||
* read papers about highway connection and multi-task.
|-

|-
|Ying Shi
||
* paper reading kazak speech recognition data prep
||
* baseline of kazak speech recoginition
|-

|-
|Yixiang Chen
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* almost finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].
||
* report for Weekly Reading;
* joint training for bilingual.
|}

ASR Status Report 2016-11-14

2016-11-17T07:47:11Z

Luohang：

{| class="wikitable"
!Date!!People !! Last Week !! This Week

|-
| rowspan="5"|2016.11.14
|Hang Luo
||
* read papers about highway connection and multi-task
||
* Explore the language recognition model on speech+language joint training, find how to use languange information.
finish ML-book
|-

|-
|Ying Shi
||
* kazaka recognition baseline finished [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=576 here]
||
* figuie of ml-book read paper nn visualization
|-

|-
|Yixiang Chen
||
* Motify the ML-book and read paper.
* Prepare the replay detection baseline.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=571]
||
* Complete the replay baseline and attempt to modify MFCC calculation.
|-

|-
|Lantian Li
||
* Complete the Joint-training on TASLP (speaker parts). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=573]
* Joint-training on SRE and LRE (Still over-fitting !). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
* Read some papers and download four database. [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Data_resources]
* CSLT-Replay detection database is OK! [/work4/lilt/Replay]
||
* Joint-training on SRE and LRE.
* Baseline system on replay detection.
|-

|-
|Zhiyuan Tang
||
* finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].
* prepare a brief review of interspeech16.
||
* report for Weekly Reading (a brief review of interspeech16);
* joint training for bilingual: language scores as decoding mask, explore the best info receivier by studying single tasks with extra info.
|}

-----------------------------------------------------------------------------------------------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week

|-
| rowspan="5"|2016.11.07
|Hang Luo
||
* make a report of 2 Inter Speech papers
* run joint training experiments and the result is [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=luohang&step=view_request&cvssid=578]
||
* read papers about highway connection and multi-task.
|-

|-
|Ying Shi
||
* paper reading kazak speech recognition data prep
||
* baseline of kazak speech recoginition
|-

|-
|Yixiang Chen
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* almost finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].
||
* report for Weekly Reading;
* joint training for bilingual.
|}