“ASR:2015-04-13”版本间的差异
来自cslt Wiki
（→Speech Processing） |
（→Speech Processing） |
||
| 第4行： | 第4行： | ||
==== Environment ==== | ==== Environment ==== | ||
* grid-11 often shut down automatically, too slow computation speed. | * grid-11 often shut down automatically, too slow computation speed. | ||
| − | * add a server | + | * add a server(760) |
==== RNN AM==== | ==== RNN AM==== | ||
| 第14行： | 第14行： | ||
==== Mic-Array ==== | ==== Mic-Array ==== | ||
* investigate alpha parameter in time domian and frquency domain | * investigate alpha parameter in time domian and frquency domain | ||
| − | * ALPHA>=0 | + | * ALPHA>=0, using data generated by reverber toolkit |
| + | * consider theta | ||
| 第28行： | 第29行： | ||
===Speaker ID=== | ===Speaker ID=== | ||
:* DNN-based sid --Yiye | :* DNN-based sid --Yiye | ||
| − | |||
:* 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 based ASR=== | ===Ivector based ASR=== | ||
| + | *hold | ||
:* 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 | :* Ivector dimention is smaller, performance is better | ||
:* Augument to hidden layer is better than input layer | :* Augument to hidden layer is better than input layer | ||
:* train on wsj(testbase dev93+evl92) | :* train on wsj(testbase dev93+evl92) | ||
| + | |||
| + | ===Dark knowledge=== | ||
| + | :*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --zhiyong | ||
| + | :* trial on logit matching faild --mengyuan | ||
| + | :* adaptation for chinglish under investigation-mengyuan | ||
| + | :* unsupervised training with wsj contributes to aurora4 model--xiangyu | ||
| + | :* test large database with amida--xiangyu | ||
| + | |||
| + | ===bilingual recognition=== | ||
| + | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359--zhiyuan | ||
==Text Processing== | ==Text Processing== | ||
2015年4月15日 (三) 07:42的最后版本
Speech Processing
AM development
Environment
- grid-11 often shut down automatically, too slow computation speed.
- add a server(760)
RNN AM
- details at http://liuc.cslt.org/pages/rnnam.html
- tuning parameters on monophone NN
- run using wsj,MPE
Mic-Array
- investigate alpha parameter in time domian and frquency domain
- ALPHA>=0, using data generated by reverber toolkit
- consider theta
Convolutive network
- HOLD
- CNN + DNN feature fusion
RNN-DAE(Deep based Auto-Encode-RNN)
- HOLD -Zhiyong
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
Speaker ID
Ivector based ASR
- hold
- 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
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --zhiyong
- trial on logit matching faild --mengyuan
- adaptation for chinglish under investigation-mengyuan
- unsupervised training with wsj contributes to aurora4 model--xiangyu
- test large database with amida--xiangyu
bilingual recognition
Text Processing
tag LM
- similar word extension in FST
- will check the formula using Bayes and experiment
- fixed the bug using the big-lm.
- will add more test data
- will test the baseline(no weight) and different weight method
RNN LM
- rnn
- code the character-lm using Theano
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based document classification
- some result about VMF model [1]
- will try max-method
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
online learning
- data is ready.prepare the ACL paper
- modified the listNet SGD
- finish some test.
- test the result on different time.
relation classifier
- modified the drop-out method
