“ASR:2015-05-04”版本间的差异
来自cslt Wiki
（以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shut down automatically, too slow computation speed. * New grid-13 added, using...”为内容创建页面） |
（→Speech Processing） |
||
| 第3行： | 第3行： | ||
==== Environment ==== | ==== Environment ==== | ||
| − | * grid- | + | * grid-15 often does not work |
| − | + | ||
| − | + | ||
==== RNN AM==== | ==== RNN AM==== | ||
* details at http://liuc.cslt.org/pages/rnnam.html | * details at http://liuc.cslt.org/pages/rnnam.html | ||
| − | * Test monophone on RNN using dark-knowledge | + | * Test monophone on RNN using dark-knowledge --Chao Liu |
| − | * run using wsj,MPE | + | * run using wsj,MPE --Chao Liu |
| + | * run bi-directon --Chao Liu | ||
| + | * modify code --Zhiyuan | ||
==== Mic-Array ==== | ==== Mic-Array ==== | ||
| 第17行： | 第17行： | ||
* ALPHA>=0, using data generated by reverber toolkit | * ALPHA>=0, using data generated by reverber toolkit | ||
* consider theta | * consider theta | ||
| + | * compute EER with kaldi | ||
====RNN-DAE(Deep based Auto-Encode-RNN)==== | ====RNN-DAE(Deep based Auto-Encode-RNN)==== | ||
| 第27行： | 第28行： | ||
===Ivector&Dvector based ASR=== | ===Ivector&Dvector based ASR=== | ||
| + | * hold --Tian Lan | ||
:* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric | :* 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. | :* Direct using the dark-knowledge strategy to do the ivector training. | ||
| 第35行： | 第37行： | ||
===Dark knowledge=== | ===Dark knowledge=== | ||
| − | :* Ensemble | + | :* 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 | ::*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang | ||
:* adaptation for chinglish under investigation --Mengyuan Zhao | :* adaptation for chinglish under investigation --Mengyuan Zhao | ||
| 第43行： | 第45行： | ||
===bilingual recognition=== | ===bilingual recognition=== | ||
| − | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang | + | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan |
==Text Processing== | ==Text Processing== | ||
2015年5月6日 (三) 08:02的版本
Speech Processing
AM development
Environment
- grid-15 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
- modify code --Zhiyuan
Mic-Array
- 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)
- HOLD --Zhiyong Zhang
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
Speaker ID
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.
- 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
- Ensemble using 100h dataset to construct diffrernt structures -- Mengyuan
- adaptation for chinglish under investigation --Mengyuan Zhao
- Try to improve the chinglish performance extremly
- unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
- test large database with AMIDA
bilingual recognition
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan
Text Processing
tag LM
- similar word extension in FST
- will check the formula using Bayes and experiment
- add similarity weight
RNN LM
- rnn
- test the ppl and code the character-lm
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based document classification
- result about norm model [1]
- try CNN model
Translation
- v5.0 demo released
- cut the dict and use new segment-tool
Sparse NN in NLP
- test the drop-out model and the performance gets a little improvement, need some result:
- test the order feature ,need some result:
- large dimension result:http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=344
- sparse-nn on 1000 dimension(le-6,0.705236) is better than 200 dimension(le-12,0.694678).
online learning
- modified the listNet SGD
relation classifier
- check the CNN code and contact the author of paper
