“ASR:2015-05-18”版本间的差异
来自cslt Wiki
（以“==Speech Processing == === AM development === ==== Environment ==== * grid-15 often does not work ==== RNN AM==== * details at http://liuc.cslt.org/pages/rnnam.htm...”为内容创建页面） |
（→Speech Processing） |
||
| 第4行： | 第4行： | ||
==== Environment ==== | ==== Environment ==== | ||
* grid-15 often does not work | * grid-15 often does not work | ||
| + | * grid-14 often does not work | ||
==== RNN AM==== | ==== RNN AM==== | ||
| 第10行： | 第11行： | ||
* run using wsj,MPE --Chao Liu | * run using wsj,MPE --Chao Liu | ||
* run bi-directon --Chao Liu | * run bi-directon --Chao Liu | ||
| − | * | + | * train RNN with dark knowledge transfer on AURORA4 --zhiyuan |
| + | :*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=383--zhiyuan | ||
==== Mic-Array ==== | ==== Mic-Array ==== | ||
| + | * hold | ||
* Change the prediction from fbank to spectrum features | * Change the prediction from fbank to spectrum features | ||
* investigate alpha parameter in time domian and frquency domain | * investigate alpha parameter in time domian and frquency domain | ||
| 第20行： | 第23行： | ||
====RNN-DAE(Deep based Auto-Encode-RNN)==== | ====RNN-DAE(Deep based Auto-Encode-RNN)==== | ||
| − | * | + | * deliver to mengyuan |
| − | * 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 |
===Speaker ID=== | ===Speaker ID=== | ||
| − | + | * DNN-based sid --Yiye Lin | |
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327 | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327 | ||
===Ivector&Dvector based ASR=== | ===Ivector&Dvector based ASR=== | ||
| − | * hold | + | * hold --Tian Lan |
| − | + | * Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric | |
| − | + | * Direct using the dark-knowledge strategy to do the ivector training. | |
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340 | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340 | ||
| − | + | * Ivector dimention is smaller, performance is better | |
| − | + | * Augument to hidden layer is better than input layer | |
| − | + | * train on wsj(testbase dev93+evl92) | |
===Dark knowledge=== | ===Dark knowledge=== | ||
| − | + | * Ensemble using 100h dataset to construct diffrernt structures -- Mengyuan | |
| − | + | :*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang | |
| − | + | * adaptation English and Chinglish | |
| − | + | :* Try to improve the chinglish performance extremly | |
| − | + | * unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng | |
| − | + | * test large database with AMIDA | |
| + | * test hidden layer knowledge transfer--xuewei | ||
===bilingual recognition=== | ===bilingual recognition=== | ||
| + | * hold | ||
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan | ||
| + | |||
| + | ===language vector=== | ||
| + | * train DNN with language vector--xuewei | ||
==Text Processing== | ==Text Processing== | ||
2015年5月20日 (三) 08:58的版本
Speech Processing
AM development
Environment
- grid-15 often does not work
- grid-14 often does not work
RNN AM
- details at http://liuc.cslt.org/pages/rnnam.html
- Test monophone on RNN using dark-knowledge --Chao Liu
- run using wsj,MPE --Chao Liu
- run bi-directon --Chao Liu
- train RNN with dark knowledge transfer on AURORA4 --zhiyuan
Mic-Array
- hold
- Change the prediction from fbank to spectrum features
- investigate alpha parameter in time domian and frquency domain
- ALPHA>=0, using data generated by reverber toolkit
- consider theta
- compute EER with kaldi
RNN-DAE(Deep based Auto-Encode-RNN)
- deliver to mengyuan
Speaker ID
- DNN-based sid --Yiye Lin
Ivector&Dvector based ASR
- hold --Tian Lan
- Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
- Direct using the dark-knowledge strategy to do the ivector training.
- Ivector dimention is smaller, performance is better
- Augument to hidden layer is better than input layer
- train on wsj(testbase dev93+evl92)
Dark knowledge
- Ensemble using 100h dataset to construct diffrernt structures -- Mengyuan
- adaptation English and Chinglish
- Try to improve the chinglish performance extremly
- unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
- test large database with AMIDA
- test hidden layer knowledge transfer--xuewei
bilingual recognition
- hold
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan
language vector
- train DNN with language vector--xuewei
Text Processing
RNN LM
- character-lm rnn(hold)
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based document classification
- make a technical report about document classification using CNN --yiqiao
- CNN adapt to resolve the low resource problem
Translation
- similar-pair method in English word using translation model.
- result:wer:70%-50% on top1.
- change the AM model
Order representation
- modify the objective function
- sup-sampling method to solve the low frequence word
binary vector
Stochastic ListNet
- using sampling method and test
relation classifier
- test the bidirectional neural network(B-RNN) and get a little improvement
plan to do
- combine LDA with neural network
