“ASR Status Report 2017-9-4”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（4位用户的7个中间修订版本未显示）
第7行： 第7行：
 
|Jiayin Cai
 
|Jiayin Cai
 
||
 
||
−
*
+
*Finished the phonetic i-vector experiment.
 
||
 
||
−
*
+
*get BN feature and train i-vector LID.
 +
*Get phonetic feat from a stronger phonetic network
 +
*combine PTN and phonetic i-vector.
 
|-
 
|-
  
第16行： 第18行：
 
|Xiaofei Kang
 
|Xiaofei Kang
 
||  
 
||  
−
*  
+
* cutting audio and marking：21 speakers，a total of 1050 sentences
 +
* Finish the new speaker recognition using the two recordings.
 
||  
 
||  
−
*  
+
* improve the human Test website
 
|-
 
|-
  
第25行： 第28行：
 
|Miao Zhang
 
|Miao Zhang
 
||  
 
||  
−
*  
+
* Absent
 
||  
 
||  
−
*  
+
* Perform human test on 21-style speech(add the disguise)
 +
* Draw spectrums and t-SNE plots compared with experiment results
 
|-
 
|-
  
第43行： 第47行：
 
|Ying Shi   
 
|Ying Shi   
 
||  
 
||  
−
*  
+
* multi decodeing ASR model
 +
* multi decodeing with fake Lid [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=627 here]
 +
* read code about TTS
 
||  
 
||  
−
*  
+
* employ group softmax to train multi decoding ASR model
 +
* synthesis one 'real' speech
 
|-
 
|-
  
第61行： 第68行：
 
|Lantian Li   
 
|Lantian Li   
 
||  
 
||  
−
*  
+
* Go on speaker segmentation tasks, see [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=615 here]
 +
** Dimensionality reduction.
 +
** Clustering.
 +
** Visualization.
 
||
 
||
−
*  
+
* Phonetic-aware speaker segmentation.
 
|-
 
|-
  

2017年9月4日 (一) 05:22的最后版本

Date People Last Week This Week
2017.9.4


Jiayin Cai
  • Finished the phonetic i-vector experiment.
  • get BN feature and train i-vector LID.
  • Get phonetic feat from a stronger phonetic network
  • combine PTN and phonetic i-vector.
Xiaofei Kang
  • cutting audio and marking：21 speakers，a total of 1050 sentences
  • Finish the new speaker recognition using the two recordings.
  • improve the human Test website
Miao Zhang
  • Absent
  • Perform human test on 21-style speech(add the disguise)
  • Draw spectrums and t-SNE plots compared with experiment results
Yanqing Wang
  • Absent.
Ying Shi
  • multi decodeing ASR model
  • multi decodeing with fake Lid here
  • read code about TTS
  • employ group softmax to train multi decoding ASR model
  • synthesis one 'real' speech
Yixiang Chen
  • Absent.
Lantian Li
  • Go on speaker segmentation tasks, see here
    • Dimensionality reduction.
    • Clustering.
    • Visualization.
  • Phonetic-aware speaker segmentation.
Zhiyuan Tang
  • more indicators for VV scoring system, see [1].
  • more indicators, a demo with Shuai.
  • toolbook writing.



Date People Last Week This Week
2017.8.21 Xiaofei Kang
  • Recording new audios from 38 person, located in /work7/tanghui/kangxf/workspaces/speaker/wavdata/V2.0
  • Improve the test website to judge before committing
  • Test the new recording。
Miao Zhang
Yanqing Wang
  • pruning the connections and refining, results
  • Absent.
Ying Shi
  • check toolkit code
  • multilingual baseline system
  • train language id model
  • use Lid to do multi-decoding
  • some experiments for zhiyong zhang about TTS
Yixiang Chen
Lantian Li
  • Attend IS2017.
  • Go on speaker segmentation tasks.
Zhiyuan Tang
  • several indicators for VV scoring system, see [2].
  • more indicators, a demo with Shuai.
  • toolbook writing.
取自“http://index.cslt.org/mediawiki/index.php?title=ASR_Status_Report_2017-9-4&oldid=28586”