“2022-01-10”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(8位用户的9个中间修订版本未显示)
第5行: 第5行:
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*  
+
* Finish CNSRC challenge plan
 +
* Deal with ICASSP response
 +
* Keep on survey for multi-modal information fusion
 
||
 
||
*  
+
* Keep on multi-modal technique review
 
||
 
||
 
*   
 
*   
第39行: 第41行:
 
|Ying Shi
 
|Ying Shi
 
||  
 
||  
*  
+
* Speech engrave (text attend speech)
 +
* attention visualization [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
 
||
 
||
*  
+
* Speech engrave v2
 
||
 
||
 
*   
 
*   
第61行: 第64行:
 
|Chen Chen
 
|Chen Chen
 
||  
 
||  
*  
+
* Finish course thesis
 +
* Test UASR with different phone symbol
 
||
 
||
*  
+
* Figure out reason of the influence of symbol
 +
* Test w2v2.0 feats with other NN instead of GAN
 
||
 
||
 
*   
 
*   
第83行: 第88行:
 
|Weida Liang
 
|Weida Liang
 
||   
 
||   
*  
+
* Finish wav2vec+decoder model and do self-evaluation test
 +
* evaluate the scale of network
 
||
 
||
*  
+
* Finish the never-before seen test
 +
* Paper sharing on Wednesday
 
||
 
||
 
*   
 
*   
第93行: 第100行:
 
|Zixi Yan
 
|Zixi Yan
 
||   
 
||   
*  
+
* Thchs30 speech recognition using Kaldi
 +
* Try using the WAV2VEc feature in Kaldi speech recognition, modify make_mfcc.sh
 
||
 
||
 
*
 
*
第103行: 第111行:
 
|Sirui Li
 
|Sirui Li
 
||   
 
||   
*  
+
* Compare the effect of wav2vec parameter tuning
 +
* Prepare group report
 
||
 
||
*  
+
* Extract Chinese features for GAN
 
||
 
||
 
*   
 
*   
第114行: 第123行:
 
|Haoyu Jiang
 
|Haoyu Jiang
 
||  
 
||  
*  
+
* Calculate the acc of each segment score
 
||
 
||
*  
+
* Complete data merge
 
||
 
||
 
*   
 
*   
第135行: 第144行:
 
|Renmiao Chen
 
|Renmiao Chen
 
||  
 
||  
 +
* Finish course task
 
||
 
||
||
+
* Finish pmi
*
+
 
|-
 
|-
  
 
|}
 
|}

2022年1月10日 (一) 11:12的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Finish CNSRC challenge plan
  • Deal with ICASSP response
  • Keep on survey for multi-modal information fusion
  • Keep on multi-modal technique review
Yunqi Cai
  • Capsnet generative model investigation
Lantian Li
  • Push CNCSRC plan
  • Make Real AM rebuttal
  • Go on hard trials paper
Ying Shi
  • Speech engrave (text attend speech)
  • attention visualization here
  • Speech engrave v2
Haoran Sun
Chen Chen
  • Finish course thesis
  • Test UASR with different phone symbol
  • Figure out reason of the influence of symbol
  • Test w2v2.0 feats with other NN instead of GAN
Pengqi Li
Weida Liang
  • Finish wav2vec+decoder model and do self-evaluation test
  • evaluate the scale of network
  • Finish the never-before seen test
  • Paper sharing on Wednesday
Zixi Yan
  • Thchs30 speech recognition using Kaldi
  • Try using the WAV2VEc feature in Kaldi speech recognition, modify make_mfcc.sh
Sirui Li
  • Compare the effect of wav2vec parameter tuning
  • Prepare group report
  • Extract Chinese features for GAN
Haoyu Jiang
  • Calculate the acc of each segment score
  • Complete data merge
Ruihai Hou
Renmiao Chen
  • Finish course task
  • Finish pmi