“ASR:2015-03-02”版本间的差异
来自cslt Wiki
（以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 has been repairing. * grid-11 often shutdown automatically, too slow com...”为内容创建页面） |
（→Text Processing） |
||
| 第65行： | 第65行： | ||
:* train a large lm using 25w-dict.(hanzhenglong/wxx) | :* train a large lm using 25w-dict.(hanzhenglong/wxx) | ||
::* v2.0a adjust the weight and smaller weight of transcription is better.(done) | ::* v2.0a adjust the weight and smaller weight of transcription is better.(done) | ||
| − | ::* v2.0b add the v1.0 vocab( | + | ::* v2.0b add the v1.0 vocab(done) |
::* v2.0c filter the useless word.(next week) | ::* v2.0c filter the useless word.(next week) | ||
::* set the test set for new word (hold) | ::* set the test set for new word (hold) | ||
| 第88行： | 第88行： | ||
* data prepare. | * data prepare. | ||
====Knowledge vector==== | ====Knowledge vector==== | ||
| − | * | + | * paper is done, submitted ACL |
| − | + | ||
| − | + | ||
| − | + | ||
====Character to word==== | ====Character to word==== | ||
* Character to word conversion(hold) | * Character to word conversion(hold) | ||
| 第111行： | 第108行： | ||
* add Synonyms similarity using MERT-4 method(hold) | * add Synonyms similarity using MERT-4 method(hold) | ||
====improve lucene search==== | ====improve lucene search==== | ||
| − | :* | + | :* commit to Rong Liu to check in. |
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
* online learning to rank | * online learning to rank | ||
:* tool is ok and ready to test | :* tool is ok and ready to test | ||
| 第125行： | 第118行： | ||
:* change to knowledge graph,and learn the D2R tool and JENA[[媒体文件:政府组织机构图谱--汇联.pdf| 政府组织推演]] [[媒体文件:员工信息推演_知识图谱.pdf|员工信息实例推演]] | :* change to knowledge graph,and learn the D2R tool and JENA[[媒体文件:政府组织机构图谱--汇联.pdf| 政府组织推演]] [[媒体文件:员工信息推演_知识图谱.pdf|员工信息实例推演]] | ||
:* code for demo | :* code for demo | ||
| − | + | ::* | |
====query normalization==== | ====query normalization==== | ||
* using NER to normalize the word | * using NER to normalize the word | ||
* new inter will install SEMPRE | * new inter will install SEMPRE | ||
2015年3月2日 (一) 05:20的版本
目录
Speech Processing
AM development
Environment
- May gpu760 of grid-14 has been repairing.
- grid-11 often shutdown automatically, too slow computation speed.
RNN AM
- details at http://liuc.cslt.org/pages/rnnam.html
Mic-Array
- XueWei is reading papers and preparing the technical report
Dropout & Maxout & rectifier
- Need to solve the too small learning-rate problem
- 20h small scale sparse dnn with rectifier. --Chao liu
- 20h small scale sparse dnn with Maxout/rectifier based on weight-magnitude-pruning. --Mengyuan Zhao
- hold
Convolutive network
- Convolutive network(DAE)
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=311
- Technical report to draft, Mian Wang, Yiye Lin, Shi Yin, Mengyuan Zhao
DNN-DAE(Deep Auto-Encode-DNN)
- Technical report to draft, Xiangyu Zeng, Shi Yin, Mengyuan Zhao and Zhiyong Zhang,
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=318
RNN-DAE(Deep based Auto-Encode-RNN)
VAD
- DAE
- HOLD
- Technical report -- Shi Yin
Speech rate training
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=268
- Technical report to draft. Xiangyu Zeng, Shi Yin
- Prepare for ChinaSIP
Confidence
- Reproduce the experiments on fisher dataset.
- Use the fisher DNN model to decode all-wsj dataset
- preparing scoring for puqiang data
- HOLD
Neural network visulization
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324
- Technical report, Mian Wang.
Speaker ID
Text Processing
LM development
Domain specific LM
- LM2.X
- mix the sougou2T-lm,kn-discount(done)
- train a large lm using 25w-dict.(hanzhenglong/wxx)
- v2.0a adjust the weight and smaller weight of transcription is better.(done)
- v2.0b add the v1.0 vocab(done)
- v2.0c filter the useless word.(next week)
- set the test set for new word (hold)
tag LM
- Tag Lm
- add 3-class tag and test
- similar word extension in FST
- improve the key-word weight in G , and result is good in keyword recognization
- read to deal with the English-Chinese
RNN LM
- rnn
- test wer RNNLM on Chinese data from jietong-data
- generate the ngram model from rnnlm and test the ppl with different size txt.
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
Word2Vector
W2V based doc classification
- data prepare.
Knowledge vector
- paper is done, submitted ACL
Character to word
- Character to word conversion(hold)
Word vector online learing
- prepare the ACL
Translation
- v5.0 demo released
- cut the dict and use new segment-tool
Sparse NN in NLP
- write a technical report(Wednesday) and make a report.
- ready to prepare the ACL
QA
improve fuzzy match
- add Synonyms similarity using MERT-4 method(hold)
improve lucene search
- commit to Rong Liu to check in.
- online learning to rank
- tool is ok and ready to test
online learning
- a simple edition about online learning part about QA.
context framework
- code for organization
query normalization
- using NER to normalize the word
- new inter will install SEMPRE
