“2023-12-18”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(12位用户的19个中间修订版本未显示)
第6行: 第6行:
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*  
+
* SIP chapter 14
 +
* Review explainability in speech processing
 +
 
 
||
 
||
 
*
 
*
第17行: 第19行:
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
*  
+
* GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh]
 +
* APT-group (ICCIP)
 +
* BlockChain Course
 
||
 
||
 
*  
 
*  
第31行: 第35行:
 
* Design TC-ASR experiments
 
* Design TC-ASR experiments
 
* revise keywords-attributed Overlapping ASR paper
 
* revise keywords-attributed Overlapping ASR paper
 +
* [https://z1et6d3xtb.feishu.cn/wiki/AYF0wiXI9iiGnwkCNc2ctuJmnWd?from=from_copylink group work]
 
||
 
||
 
* Finish draft of keywords-attributed Overlapping ASR paper
 
* Finish draft of keywords-attributed Overlapping ASR paper
第41行: 第46行:
 
|Zhenghai You
 
|Zhenghai You
 
||  
 
||  
*  
+
* Target Speech Separation Exp [https://z1et6d3xtb.feishu.cn/wiki/V8aBwiLteirIUFkTNMocXkMBn71 here]
 +
* Software Copyright [https://z1et6d3xtb.feishu.cn/docx/ZJbgd02Ato17TKxoXFucR9sCnkf here]
 +
* BlockChain Course
 
||
 
||
 
*  
 
*  
第64行: 第71行:
 
||  
 
||  
 
* Data Collection Website (finish in one week)
 
* Data Collection Website (finish in one week)
 +
* VII Group [https://z1et6d3xtb.feishu.cn/docx/REyudXfi1o3BooxIlUFc2W84nDd?from=from_copylink]
 
||
 
||
 
* Data Collection Website (finish in one week)
 
* Data Collection Website (finish in one week)
第74行: 第82行:
 
|Xiaolou Li
 
|Xiaolou Li
 
||  
 
||  
*  
+
* Inter ctc and Paper reading
 
||
 
||
 
*  
 
*  
第85行: 第93行:
 
|Zehua Liu
 
|Zehua Liu
 
||  
 
||  
*  
+
* VSR-Data-exp[https://z1et6d3xtb.feishu.cn/docx/Kp94dXZMdoVC7SxAk0DcbJvpnDg?from=from_copylink]
 
||
 
||
 
*  
 
*  
第96行: 第104行:
 
|Pengqi Li
 
|Pengqi Li
 
||   
 
||   
*  
+
* workshop paper
 +
* Team work[https://z1et6d3xtb.feishu.cn/docx/XDsVdXGIxo2Dn9x5Dp8csN42nDg]
 
||
 
||
 
*
 
*
第107行: 第116行:
 
|Wan Lin
 
|Wan Lin
 
||  
 
||  
*
+
* IS2023 paper reading
 
||
 
||
 
*
 
*
第118行: 第127行:
 
|Tianhao Wang
 
|Tianhao Wang
 
||  
 
||  
*  
+
* layer ablation exps [https://z1et6d3xtb.feishu.cn/docx/EceCdu0eKoMuf8xXDjoc6wUInxf]
 +
* read paper
 
||
 
||
 
*  
 
*  
第139行: 第149行:
 
|-
 
|-
 
|Junhui Chen
 
|Junhui Chen
 +
||
 +
* mix test on EA-ASP-Eval[https://z1et6d3xtb.feishu.cn/docx/DUmEdjSdNoZU5zxbrnxcvrZhnne#EavEdDh0uodEscxAuHGcrVaynBc]
 +
* Model modification
 
||
 
||
 
*  
 
*  
||
 
*
 
 
||
 
||
 
*   
 
*   
第162行: 第173行:
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
*  
+
* software copy right
 +
* financial pipeline
 
||
 
||
 
*
 
*
第173行: 第185行:
 
|Wenqiang Du
 
|Wenqiang Du
 
||  
 
||  
*  
+
* Some project cooperation
 +
* homework
 
||
 
||
 
*
 
*
第184行: 第197行:
 
|Yang Wei
 
|Yang Wei
 
||  
 
||  
*  
+
* Support huilan ASR project
 +
* Another test for Chinese audio visual speech separation
 
||
 
||
 
*
 
*

2023年12月18日 (一) 11:00的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • SIP chapter 14
  • Review explainability in speech processing
Lantian Li
  • GPU status [1]
  • APT-group (ICCIP)
  • BlockChain Course
Ying Shi
  • Design SOT experiments
  • Design TC-ASR experiments
  • revise keywords-attributed Overlapping ASR paper
  • group work
  • Finish draft of keywords-attributed Overlapping ASR paper
Zhenghai You
  • Target Speech Separation Exp here
  • Software Copyright here
  • BlockChain Course
Junming Yuan
  • keyword-specific Conv + FC
  • ICCIP slide
Chen Chen
  • Data Collection Website (finish in one week)
  • VII Group [2]
  • Data Collection Website (finish in one week)
Xiaolou Li
  • Inter ctc and Paper reading
Zehua Liu
  • VSR-Data-exp[3]
Pengqi Li
  • workshop paper
  • Team work[4]
Wan Lin
  • IS2023 paper reading
Tianhao Wang
  • layer ablation exps [5]
  • read paper
Zhenyu Zhou
  • iccip conference
Junhui Chen
  • mix test on EA-ASP-Eval[6]
  • Model modification
Jiaying Wang
  • iccip conference
Yu Zhang
  • software copy right
  • financial pipeline
Wenqiang Du
  • Some project cooperation
  • homework
Yang Wei
  • Support huilan ASR project
  • Another test for Chinese audio visual speech separation