“2023-10-16”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“{| class="wikitable" !People !! This Week !! Next Week !! Task Tracking (<font color="red">DeadLine</font>) |- |- |Dong Wang || * || * || * |- |- |Lantian Li |...”为内容创建页面)
 
 
(15位用户的19个中间修订版本未显示)
第2行: 第2行:
 
!People !! This Week !! Next Week !! Task Tracking (<font color="red">DeadLine</font>)
 
!People !! This Week !! Next Week !! Task Tracking (<font color="red">DeadLine</font>)
 
|-
 
|-
 +
 
|-
 
|-
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*
+
* SIP chapter 5
 +
* AIBook experiment doc
 +
* Two public talk
  
 
||
 
||
第17行: 第20行:
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
*  
+
* GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh]
 +
* APT-group
 +
* DeepTrader (TG-SAC)
 
||
 
||
 
*  
 
*  
第23行: 第28行:
 
*   
 
*   
 
|-
 
|-
 +
 +
 
|-
 
|-
 
|Ying Shi
 
|Ying Shi
 
||  
 
||  
*
+
* Speaker attributed speech separation
 +
* Diting-2 phase 3
 +
* Re-train  WaveGAN
 +
* An idea [https://z1et6d3xtb.feishu.cn/docx/BdGmdAY8soCtajxjj0FczhQznrc here]
 +
||
 +
*
 +
||
 +
 +
|-
 +
 
 +
 
 +
|-
 +
|Zhenghai You
 +
||
 +
* Wrap or  Zero Padding in SR [https://z1et6d3xtb.feishu.cn/docx/WpbydyxUwobnd1xA1U6cxmOLnig here]
 +
* AI-Demo [https://z1et6d3xtb.feishu.cn/docx/SGpJdma3soPC0Ux3X1ac0sZjnTc here]
 
||
 
||
 
*  
 
*  
第37行: 第59行:
 
|Chen Chen
 
|Chen Chen
 
||  
 
||  
 +
* vts experiments [https://z1et6d3xtb.feishu.cn/docx/QV7pdhunMoSeAqxR0JzcSOuwnWf?from=from_copylink]
 +
* cnvsrc scheduler [https://z1et6d3xtb.feishu.cn/docx/ICo8dlG4joogv5x5DXZcfPfznHg?from=from_copylink]
 +
* audio-visual data collect [https://z1et6d3xtb.feishu.cn/docx/V6yHddY2fosUxqxq13BcvW14ng0?from=from_copylink]
 +
||
 
*  
 
*  
 +
||
 +
 +
|-
 +
 +
 +
|-
 +
|Xiaolou Li
 +
||
 +
* LM[https://z1et6d3xtb.feishu.cn/docx/ZseRd7dj1ogvT3x5R5VcrcPcnbg?from=from_copylink]
 +
||
 +
*
 +
||
 +
 +
|-
 +
 +
 +
|-
 +
|Zehua Liu
 +
||
 +
* VTS[https://z1et6d3xtb.feishu.cn/docx/KYDZdVnBuoE5sUxFIu8cqVifnCw?from=from_copylink]
 +
* Data aug[https://z1et6d3xtb.feishu.cn/docx/EM4udVJwGo9kGqxUDcdcqO8nn8b?from=from_copylink]
 
||
 
||
 
*  
 
*  
第48行: 第95行:
 
|Pengqi Li
 
|Pengqi Li
 
||   
 
||   
*  
+
* Phone's discrimination in deep SID [https://z1et6d3xtb.feishu.cn/docx/R8mUdlG2goLjphxQCk6c5zYhn5e]
 +
* concat silence[https://z1et6d3xtb.feishu.cn/docx/QdzJdXnFRoAMMix8bQIc6vf7nUb]
 
||
 
||
 
*
 
*
第57行: 第105行:
  
 
|-
 
|-
 
 
|Wan Lin
 
|Wan Lin
 
||  
 
||  
*  
+
* NC paper [https://z1et6d3xtb.feishu.cn/docx/FFJWdOIYgovVN4xoCN4cxmIynWf?from=from_copylink]
 
||
 
||
 
*
 
*
第71行: 第118行:
 
|Tianhao Wang
 
|Tianhao Wang
 
||  
 
||  
*  
+
* Block SE importance exp [https://z1et6d3xtb.feishu.cn/docx/EceCdu0eKoMuf8xXDjoc6wUInxf]
 +
* T-PSDA exp [https://z1et6d3xtb.feishu.cn/docx/So4sd56lQokQJXxlwljcpoW8n2e]
 +
* VoxTube DataSet dl ok
 
||
 
||
 
*
 
*
第82行: 第131行:
 
|Zhenyu Zhou
 
|Zhenyu Zhou
 
||  
 
||  
*
+
*Augmentation adversarial training[https://z1et6d3xtb.feishu.cn/docx/HUJ8dPPhqo53mFx9DwVcvGPynnf]
 
||
 
||
 
*  
 
*  
第91行: 第140行:
  
 
|-
 
|-
|Jiaying Wang
+
|Junhui Chen
||  
+
||
 +
*patch BCE/CE[https://z1et6d3xtb.feishu.cn/docx/H0hidEswqo3Kz4xrnCZcfDx7nxb?from=from_copylink]
 +
||
 
*
 
*
||
 
*
 
 
||
 
||
 
*   
 
*   
第102行: 第151行:
  
 
|-
 
|-
|Xiaolou Li
+
|Jiaying Wang
 
||  
 
||  
*  
+
* Beam search[https://z1et6d3xtb.feishu.cn/sheets/CR4ms6T2ohT4mltXc6cci1HPnsh]
 
||
 
||
 
*  
 
*  
第113行: 第162行:
  
 
|-
 
|-
|Junhui Chen
+
|Yu Zhang
 
||
 
||
*
+
* AI demo
 +
* beam search
 
||
 
||
 
*
 
*
第121行: 第171行:
 
*   
 
*   
 
|-
 
|-
 +
 +
 
|-
 
|-
 
|Wenqiang Du
 
|Wenqiang Du
 
||  
 
||  
*
+
* release model for fyt
 
||
 
||
 
*
 
*
第130行: 第182行:
 
*   
 
*   
 
|-
 
|-
 +
 +
 
|-
 
|-
 
|Yang Wei
 
|Yang Wei
 
||  
 
||  
*
+
* Investigate audio-visual speech separation
 
||
 
||
 
*
 
*

2023年10月16日 (一) 11:07的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • SIP chapter 5
  • AIBook experiment doc
  • Two public talk
Lantian Li
  • GPU status [1]
  • APT-group
  • DeepTrader (TG-SAC)
Ying Shi
  • Speaker attributed speech separation
  • Diting-2 phase 3
  • Re-train WaveGAN
  • An idea here
Zhenghai You
  • Wrap or Zero Padding in SR here
  • AI-Demo here
Chen Chen
  • vts experiments [2]
  • cnvsrc scheduler [3]
  • audio-visual data collect [4]
Xiaolou Li
Zehua Liu
Pengqi Li
  • Phone's discrimination in deep SID [8]
  • concat silence[9]
Wan Lin
Tianhao Wang
  • Block SE importance exp [11]
  • T-PSDA exp [12]
  • VoxTube DataSet dl ok
Zhenyu Zhou
  • Augmentation adversarial training[13]
Junhui Chen
Jiaying Wang
Yu Zhang
  • AI demo
  • beam search
Wenqiang Du
  • release model for fyt
Yang Wei
  • Investigate audio-visual speech separation