“ASR Status Report 2017-6-19”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“{| class="wikitable" !Date!!People !! Last Week !! This Week |- | rowspan="7"|2017.6.19 |Miao Zhang || * || * |- |- |Hui Tang || * || * |- |- |Yanqing...”为内容创建页面)
 
 
(2位用户的5个中间修订版本未显示)
第7行: 第7行:
 
|Miao Zhang
 
|Miao Zhang
 
||  
 
||  
*  
+
* publish the 2017AP paper
 
||  
 
||  
*  
+
* study ivector system and deep feature method
 
|-
 
|-
  
第15行: 第15行:
 
|Hui Tang  
 
|Hui Tang  
 
||  
 
||  
*  
+
* test the overlapped speech for a person  [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2a/Summary_6_16.pdf summary]
 +
* help jiayu use our toolkit
 
||  
 
||  
*  
+
* set a simple demo for speaker diarization
 
|-
 
|-
  
第33行: 第34行:
 
|Ying Shi   
 
|Ying Shi   
 
||  
 
||  
*  
+
* paper for APSIPA2017(kazak speech recognition)
 
||  
 
||  
*  
+
* finish this paper
 
|-
 
|-
  
第42行: 第43行:
 
|Yixiang Chen   
 
|Yixiang Chen   
 
||  
 
||  
*  
+
* work for APSIPA2017
 
||  
 
||  
*  
+
* finish this paper
 
|-
 
|-
  

2017年6月19日 (一) 04:32的最后版本

Date People Last Week This Week
2017.6.19


Miao Zhang
  • publish the 2017AP paper
  • study ivector system and deep feature method
Hui Tang
  • test the overlapped speech for a person summary
  • help jiayu use our toolkit
  • set a simple demo for speaker diarization
Yanqing Wang
  • absent.
  • absent.
Ying Shi
  • paper for APSIPA2017(kazak speech recognition)
  • finish this paper
Yixiang Chen
  • work for APSIPA2017
  • finish this paper
Lantian Li
Zhiyuan Tang
  • publish the AP17 challenge with paper.
  • package auto-scoring system.




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.