“ASR Status Report 2017-6-12”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（某位用户的一个中间修订版本未显示）
第36行： 第36行：
 
||  
 
||  
 
* LID for ASR but the performance is bad
 
* LID for ASR but the performance is bad
−
* write paper (a large scale database for kazakh speech recognition )
+
* write paper (a large scale database for kazakh speech recognition)
 
||  
 
||  
 
* finish the paper today
 
* finish the paper today
第54行： 第54行：
 
|Lantian Li   
 
|Lantian Li   
 
||  
 
||  
−
*  
+
* Deep speaker feature learning with a larger ASR model.
 +
** Speaker verification, identification and cross-lingual have been done.
 +
* End-to-end ASV.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=611]
 
||  
 
||  
−
*  
+
* Write APSIPA 2017 paper.
 +
* Speaker diarization.
 
|-
 
|-
  

2017年6月13日 (二) 04:20的最后版本

Date People Last Week This Week
2017.6.12


Miao Zhang
Hui Tang
  • by using dnn model and tsne to find the relationship between overlap speech and original voice
  • ans
  • find some information about this
Yanqing Wang
  • absent.
Ying Shi
  • LID for ASR but the performance is bad
  • write paper (a large scale database for kazakh speech recognition)
  • finish the paper today
Yixiang Chen
Lantian Li
  • Deep speaker feature learning with a larger ASR model.
    • Speaker verification, identification and cross-lingual have been done.
  • End-to-end ASV.[1]
  • Write APSIPA 2017 paper.
  • Speaker diarization.
Zhiyuan Tang
  • Recipes for AP17-OLR, OC17-MixASR.
  • Publish the AP17 challenge with paper.
Date People Last Week This Week
2017.5.31


Hui Tang
  • after introducing beamforming, zhiyong lets me learn something about how to sound localization
  • Create a database for overlapping speech
Yanqing Wang
  • continue the experiment
Ying Shi
  • work for Apsipa17
    • thchs baseline
    • kazakh baseline
    • uyghur baseline
    • 3 language merge GMM baseline
  • work for Apsipa17
  • graduation thesis
Yixiang Chen
Lantian Li
  • Submit the Interspeech paper.
  • Deep speaker feature learning with a larger ASR model.
  • Prepare the end-to-end ASV.
  • End-to-end ASV.
Zhiyuan Tang
  • Experiments for OC17 mix-asr challenge,baseline done.
  • Spk feature as LID input.
  • Data preparation for AP17 orl challenge.
  • Two challenges done.
取自“http://cslt.org/mediawiki/index.php?title=ASR_Status_Report_2017-6-12&oldid=27444”