“ASR Status Report 2016-11-21”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第73行： 第73行：
  
 
|-
 
|-
−
| rowspan="5"|2016.11.07
+
| rowspan="5"|2016.11.14
 
|Hang Luo   
 
|Hang Luo   
 
||
 
||
−
*  make a report of 2 Inter Speech papers  
+
*  read papers about highway connection and multi-task
−
*  run joint training experiments and the result is [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=luohang&step=view_request&cvssid=578]
+
 
||  
 
||  
−
*  read papers about highway connection and multi-task.
+
*  Explore the language recognition model on speech+language joint training, find how to use languange information.
 +
*  finish ML-book
 
|-  
 
|-  
  
第87行： 第87行：
 
|Ying Shi   
 
|Ying Shi   
 
||  
 
||  
−
*  paper reading kazak speech recognition data prep
+
*  kazaka recognition baseline finished [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=576  here]
 
||  
 
||  
−
*  baseline of kazak speech recoginition
+
*  figuie of ml-book read paper nn visualization
 
|-
 
|-
 +
  
  
第96行： 第97行：
 
|Yixiang Chen   
 
|Yixiang Chen   
 
||  
 
||  
−
*  
+
* Motify the ML-book and read paper.
 +
* Prepare the replay detection baseline.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=571]
 
||  
 
||  
−
*  
+
* Complete the replay baseline and attempt to modify MFCC calculation.
 
|-
 
|-
−
 
−
 
  
  
第107行： 第107行：
 
|Lantian Li   
 
|Lantian Li   
 
||  
 
||  
−
*  
+
* Complete the Joint-training on TASLP (speaker parts). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=573]
 +
* Joint-training on SRE and LRE (Still over-fitting !). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
 +
* Read some papers and download four database. [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Data_resources]
 +
* CSLT-Replay detection database is OK! [/work4/lilt/Replay]
 
||  
 
||  
−
*  
+
* Joint-training on SRE and LRE.
 +
* Baseline system on replay detection.
 
|-
 
|-
  
第116行： 第120行：
 
|Zhiyuan Tang  
 
|Zhiyuan Tang  
 
||  
 
||  
−
* almost finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].  
+
* finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=570].
 +
* prepare a brief review of interspeech16.
 
||  
 
||  
−
* report for Weekly Reading;
+
* report for Weekly Reading (a brief review of interspeech16);
−
* joint training for bilingual.
+
* joint training for bilingual: language scores as decoding mask, explore the best info receivier by studying single tasks with extra info.
 
|}
 
|}

2016年11月21日 (一) 00:40的版本

Date People Last Week This Week


2016.11.14 Hang Luo
Ying Shi
  • fighting with kazak speech recognition system:because the huge size of HCLG.fst the decoding job always make the sever done.

There are several method I have tried

  • change the size or word list and corpus this method not worked very well
  • prune the LM .And the parameter been used to prune the LM is 2e-7 the size of LM reduce from 290M to 60M but the result about wer is very poor
  • I have upload some result about several experiment to CVSS (I ought to put a link here but I modify the page is my dormitory so I can't visit CVSS so...)
  • there are too much private affairs about myself so the job about visualization last week has been delayed I will try my best to finish it the week



Yixiang Chen
Lantian Li
Zhiyuan Tang



Date People Last Week This Week


2016.11.14 Hang Luo
  • read papers about highway connection and multi-task
  • Explore the language recognition model on speech+language joint training, find how to use languange information.
  • finish ML-book
Ying Shi
  • kazaka recognition baseline finished here
  • figuie of ml-book read paper nn visualization
Yixiang Chen
  • Motify the ML-book and read paper.
  • Prepare the replay detection baseline.[1]
  • Complete the replay baseline and attempt to modify MFCC calculation.
Lantian Li
  • Complete the Joint-training on TASLP (speaker parts). [2]
  • Joint-training on SRE and LRE (Still over-fitting !). [3]
  • Read some papers and download four database. [4]
  • CSLT-Replay detection database is OK! [/work4/lilt/Replay]
  • Joint-training on SRE and LRE.
  • Baseline system on replay detection.
Zhiyuan Tang
  • finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[5].
  • prepare a brief review of interspeech16.
  • report for Weekly Reading (a brief review of interspeech16);
  • joint training for bilingual: language scores as decoding mask, explore the best info receivier by studying single tasks with extra info.
取自“http://index.cslt.org/mediawiki/index.php?title=ASR_Status_Report_2016-11-21&oldid=23914”