“ASR:2015-08-10”版本间的差异
来自cslt Wiki
（以“==Speech Processing == === AM development === ==== Environment ==== * grid-14 is on repairation * prepare to buy a server ==== RNN AM==== *hold *morpheme RNN --z...”为内容创建页面） |
（→Speech Processing） |
||
| （2位用户的2个中间修订版本未显示） | |||
| 第5行： | 第5行： | ||
* grid-14 is on repairation | * grid-14 is on repairation | ||
* prepare to buy a server | * prepare to buy a server | ||
| − | |||
==== RNN AM==== | ==== RNN AM==== | ||
*hold | *hold | ||
| − | *morpheme RNN --zhiyuan | + | *train morpheme RNN --zhiyuan |
*train using 1400h large dataset--mengyuan | *train using 1400h large dataset--mengyuan | ||
| − | *write code to tune learning rate | + | *write code to tune learning rate--zhiyong |
==== Mic-Array ==== | ==== Mic-Array ==== | ||
| 第19行： | 第18行： | ||
====Data selection unsupervised learning | ====Data selection unsupervised learning | ||
* hold | * hold | ||
| − | * acoustic feature based submodular using | + | * acoustic feature based submodular using Pingan dataset --zhiyong |
* write code to speed up --zhiyong | * write code to speed up --zhiyong | ||
| 第25行： | 第24行： | ||
====RNN-DAE(Deep based Auto-Encode-RNN)==== | ====RNN-DAE(Deep based Auto-Encode-RNN)==== | ||
* hold | * hold | ||
| − | * deliver to mengyuan | + | * deliver to mengyuan, xuewei |
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261 | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261 | ||
| 第54行： | 第53行： | ||
===monophone=== | ===monophone=== | ||
* hold | * hold | ||
| − | * triphone is tranfered to monophone | + | * triphone is tranfered to monophone--zhiyong |
| + | |||
| + | ===multi-GPU==== | ||
| + | * multi-stream training --Sheng Su | ||
==Text Processing== | ==Text Processing== | ||
| 第66行： | 第68行： | ||
====RNN Rank Task==== | ====RNN Rank Task==== | ||
| + | :*Paper: RNN Rank Net. | ||
* (hold) | * (hold) | ||
| + | |||
| + | ====Graph RNN==== | ||
| + | :* Entity path embeded to entity. | ||
| + | *(hold) | ||
====RNN Word Segment==== | ====RNN Word Segment==== | ||
| + | :* Set bound to word segment. | ||
* (hold) | * (hold) | ||
| 第86行： | 第94行： | ||
:*LDA matrix dissovle. | :*LDA matrix dissovle. | ||
:* LDA (Text classification & Recommendation System) --> AAAI | :* LDA (Text classification & Recommendation System) --> AAAI | ||
| − | |||
| − | |||
| − | |||
| − | |||
====RNN based QA==== | ====RNN based QA==== | ||
*Read Source Code. | *Read Source Code. | ||
| + | *Attention based QA. | ||
| + | *(hold) | ||
| + | |||
| + | ====RNN Poem Process==== | ||
| + | *Seq based BP. | ||
===Text Group Intern Project=== | ===Text Group Intern Project=== | ||
====Buddhist Process==== | ====Buddhist Process==== | ||
(hold) | (hold) | ||
| + | |||
====RNN Poem Process==== | ====RNN Poem Process==== | ||
| − | * | + | *Done by Haichao yu & Chaoyuan zuo Mentor : Tianyi Luo. |
====RNN Document Vector==== | ====RNN Document Vector==== | ||
(hold) | (hold) | ||
| + | |||
====Image Baseline==== | ====Image Baseline==== | ||
:*Demo Release. | :*Demo Release. | ||
| 第112行： | 第123行： | ||
====Match RNN ==== | ====Match RNN ==== | ||
* (Hold) | * (Hold) | ||
| − | |||
=financial group= | =financial group= | ||
| 第121行： | 第131行： | ||
===strategy=== | ===strategy=== | ||
* rule optimize model | * rule optimize model | ||
| − | :* | + | :* Adaboost method |
* technology index | * technology index | ||
:* survey the current technology index | :* survey the current technology index | ||
| 第128行： | 第138行： | ||
===display platform=== | ===display platform=== | ||
| − | * | + | * set up the test platform in our grid |
2015年8月10日 (一) 07:51的最后版本
目录
- 1 Speech Processing
- 2 Text Processing
- 3 financial group
Speech Processing
AM development
Environment
- grid-14 is on repairation
- prepare to buy a server
RNN AM
- hold
- train morpheme RNN --zhiyuan
- train using 1400h large dataset--mengyuan
- write code to tune learning rate--zhiyong
Mic-Array
- hold
- compute EER with kaldi
====Data selection unsupervised learning
- hold
- acoustic feature based submodular using Pingan dataset --zhiyong
- write code to speed up --zhiyong
RNN-DAE(Deep based Auto-Encode-RNN)
- hold
- deliver to mengyuan, xuewei
Speaker ID
- DNN-based sid --Lantian
Ivector&Dvector based ASR
- hold --Tian Lan
- Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
- dark-konowlege using i-vector
- train on wsj(testbase dev93+evl92)
- --hold
language vector
- hold
- train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
- hold
- write a paper--zhiyuan
- RNN language vector
- train as a paper--xuewei
rectifier
- hold
- rectifier RNN --zhiyuan
monophone
- hold
- triphone is tranfered to monophone--zhiyong
multi-GPU=
- multi-stream training --Sheng Su
Text Processing
RNN LM
- character-lm rnn(hold)
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
Neural Based Document Classification
- (hold)
RNN Rank Task
- Paper: RNN Rank Net.
- (hold)
Graph RNN
- Entity path embeded to entity.
- (hold)
RNN Word Segment
- Set bound to word segment.
- (hold)
Seq to Seq(09-15)
- Review papers.
- Reproduce baseline. (08-03)
Order representation
- Nested Dropout
- semi-linear --> neural based auto-encoder.
- modify the objective function(hold)
Balance Representation
- Find error signal
Recommendation
- Reproduce baseline.
- LDA matrix dissovle.
- LDA (Text classification & Recommendation System) --> AAAI
RNN based QA
- Read Source Code.
- Attention based QA.
- (hold)
RNN Poem Process
- Seq based BP.
Text Group Intern Project
Buddhist Process
(hold)
RNN Poem Process
- Done by Haichao yu & Chaoyuan zuo Mentor : Tianyi Luo.
RNN Document Vector
(hold)
Image Baseline
- Demo Release.
- Paper Report.
- Read CNN Paper.
Text Intuitive Idea
Trace Learning
- (Hold)
Match RNN
- (Hold)
financial group
tonglian platform
- learn the platform
- arma,ar,boosting tree is done
strategy
- rule optimize model
- Adaboost method
- technology index
- survey the current technology index
- NN
- RNN model using Theano
display platform
- set up the test platform in our grid
