“ASR:2015-04-08”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（清空页面）
Zxw（讨论 | 贡献）
第1行： 第1行：
 +
==Speech Processing ==
 +
=== AM development ===
  
 +
==== Environment ====
 +
* grid-11 often shut down automatically, too slow computation speed.
 +
 +
 +
==== 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
 +
 +
 +
====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=== 
 +
:* DNN-based sid --Yiye
 +
:* Decode --Yiye
 +
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327
 +
 +
===Ivector based ASR===
 +
:* 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)
 +
 +
==Text Processing==
 +
===tag LM===
 +
* similar word extension in FST
 +
:* check the formula using Bayes and experiment
 +
 +
====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 doc classification====
 +
* corpus ready
 +
* learn some benchmark.
 +
 +
===Translation===
 +
* v5.0 demo released
 +
:* cut the dict and use new segment-tool
 +
 +
===Sparse NN in NLP===
 +
* prepare the ACL
 +
:* check the code to find the problem .
 +
:* increase the dimension
 +
:* use different test set,but the result is not good.
 +
 +
===online learning===
 +
* data is ready.prepare the ACL paper
 +
:* prepare sougouQ data and test it using current online learning method
 +
:* baseline is not normal.

2015年4月8日 (三) 07:27的版本

Speech Processing

AM development

Environment

  • grid-11 often shut down automatically, too slow computation speed.


RNN AM


Mic-Array

  • investigate alpha parameter in time domian and frquency domain
  • ALPHA>=0


Convolutive network

  • HOLD
  • CNN + DNN feature fusion

RNN-DAE(Deep based Auto-Encode-RNN)


Speaker ID

Ivector based ASR

Text Processing

tag LM

  • similar word extension in FST
  • check the formula using Bayes and experiment

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 doc classification

  • corpus ready
  • learn some benchmark.

Translation

  • v5.0 demo released
  • cut the dict and use new segment-tool

Sparse NN in NLP

  • prepare the ACL
  • check the code to find the problem .
  • increase the dimension
  • use different test set,but the result is not good.

online learning

  • data is ready.prepare the ACL paper
  • prepare sougouQ data and test it using current online learning method
  • baseline is not normal.
取自“http://index.cslt.org/mediawiki/index.php?title=ASR:2015-04-08&oldid=14534”