“ASR:2015-04-27”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 ==== | ||
| − | + | * To update the wiki enviroment infomation --done | |
| − | + | ||
| − | * To update the wiki enviroment infomation | + | |
==== RNN AM==== | ==== RNN AM==== | ||
| + | * hold -- Chao Liu | ||
* 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 | ||
| 第16行： | 第15行： | ||
* investigate alpha parameter in time domian and frquency domain | * investigate alpha parameter in time domian and frquency domain | ||
* ALPHA>=0, using data generated by reverber toolkit | * ALPHA>=0, using data generated by reverber toolkit | ||
| − | * consider theta | + | * consider theta |
| + | * make spectrom feature with Kaldi | ||
====RNN-DAE(Deep based Auto-Encode-RNN)==== | ====RNN-DAE(Deep based Auto-Encode-RNN)==== | ||
| 第27行： | 第27行： | ||
===Ivector&Dvector based ASR=== | ===Ivector&Dvector based ASR=== | ||
| − | :* 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 -- Tian Lan |
| − | :* Direct using the dark-knowledge strategy to do the ivector training | + | :* Direct using the dark-knowledge strategy to do the ivector training -- Tian Lan |
:* 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 | ||
| − | |||
| − | |||
| − | |||
===Dark knowledge=== | ===Dark knowledge=== | ||
| − | :* Ensemble | + | :* Ensemble --Zhiyong Zhang |
::*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 | ||
| − | + | :* chinglish adaptation task best performane is obtained ofrom retraining , dark knowledge helps adapt model,try to tune papameters layear by layer ,change cv --Mengyuan Zhao | |
:* unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng | :* unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng | ||
::* test large database with AMIDA | ::* test large database with AMIDA | ||
2015年4月29日 (三) 08:00的最后版本
目录
Speech Processing
AM development
Environment
- To update the wiki enviroment infomation --done
RNN AM
- hold -- Chao Liu
- details at http://liuc.cslt.org/pages/rnnam.html
- Test monophone on RNN using dark-knowledge
- run using wsj,MPE
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
- make spectrom feature 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
- Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric -- Tian Lan
- Direct using the dark-knowledge strategy to do the ivector training -- Tian Lan
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340
Dark knowledge
- Ensemble --Zhiyong Zhang
- adaptation for chinglish under investigation --Mengyuan Zhao
- chinglish adaptation task best performane is obtained ofrom retraining , dark knowledge helps adapt model,try to tune papameters layear by layer ,change cv --Mengyuan Zhao
- unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
- test large database with AMIDA
