“2025-10-20”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（16位用户的20个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
*  
+
* Travel to Zhenjiang
 +
* AI+ project design
 +
* AI textbook 2nd semester, primary school version (3 grad)
  
 
||
 
||
第18行： 第20行：
 
|Lantian Li
 
|Lantian Li
 
||
 
||
−
*  
+
* Review AI Book – College Edition (40/53).
 +
* Submit Professional title evaluation.
 +
* Prepare the 1st delivery report for HUAWEI.
 
||
 
||
 
*
 
*
第29行： 第33行：
 
|Ying Shi
 
|Ying Shi
 
||
 
||
−
*  
+
* prepared for interviews
 +
* report some experiments on MD tasks
 
||
 
||
 
*  
 
*  
第41行： 第46行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*  
+
* AATC2025 baseline report in NC
 +
* Support for the Huawei SS project
 +
* Midreport
 
||
 
||
 
*
 
*
第51行： 第58行：
 
|Junming Yuan
 
|Junming Yuan
 
||
 
||
−
*  
+
* Evaluating the performance of MT-HuBERT on the speaker diarization task.
 +
** DER(%)result: MT-HuBERT(3.93) < Cocktail-HuBERT(4.07) < WavLM-BASE(4.55) < MPC-HuBERT(4.83) < HuBERT-BASE(5.88)
 +
* Start checking the resources for the middle-school AI course with Pengqi and Qiang bro(PPT, teaching plans).
 
||
 
||
 
*
 
*
第62行： 第71行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*  
+
* Prepared and attended NCMMSC 2025
 
||
 
||
 
*  
 
*  
第73行： 第82行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
*VSR topic training for midterm（cer：39% better than 41%）
 
||
 
||
 
*
 
*
第84行： 第93行：
 
|Pengqi Li
 
|Pengqi Li
 
||
 
||
−
*
+
* Try to Explain for hard-trials(Prof.Li previous work).
 +
* Outline the paper new structure.
 
||
 
||
 
*
 
*
第95行： 第105行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*  
+
* NCMMSC 2025
 
||
 
||
 
*
 
*
第106行： 第116行：
 
|Tianhao Wang
 
|Tianhao Wang
 
||
 
||
−
*  
+
* writing paper
 +
* Midreport
 
||
 
||
 
*
 
*
第117行： 第128行：
 
|Xiaoxue Luo
 
|Xiaoxue Luo
 
||
 
||
−
*  
+
* train of attractor-based speech separation
 +
** The loss is abnormal, possibly due to the limited distinguishability of the mask, and further adjustments are needed
 +
* Preparing for my thesis proposal
 
||
 
||
 
*
 
*
第128行： 第141行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* Keeps running & debugging reflection metric collection with @ZhangYu
 +
* Collecting & reading papers from NIPS & COLM 2025
 +
 
 
||
 
||
 
*
 
*
第139行： 第154行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* convtasnet pit & loudness order exp and visulization analyse
 +
* mid-term report
 +
** Report framework diagram
 +
** Report progress: The first part of the research and the PIT-related experimental section have been completed.
 
||
 
||
 
*
 
*
第150行： 第168行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*  
+
* Training MIC to VPU converter for Huawei AED
 +
* Keeps running & debugging reflection metric collection with @chenjunhui
 
||
 
||
 
*
 
*
第161行： 第180行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*  
+
* BUPT anniversary exhibition preparation
 +
* Check primary AI handbook（done）and related PPT、Jiaoan(6/44)
 
||
 
||
 
*
 
*
第172行： 第192行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*  
+
* Fix some bugs of the MD training code. (Not work, bce loss > 0.4)
 +
** stop inserting special token on phone sequence
 +
** correct Whisper speech embedding batch mask
 +
** add segment embedding and separate token embedding to identify the two modality
 
||
 
||
 
*
 
*
第183行： 第206行：
 
|Yue Gu
 
|Yue Gu
 
||
 
||
−
*  
+
* prepare for the writing test of the civil service exam
 +
* almost finish the structure of my thesis
 
||
 
||
 
*
 
*
第192行： 第216行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* Development for elderly alarm customization.
 +
* Perf test for vision tasks (face detection, face tracking, etc.) across candidate ROS main boards.
 +
* (In progress) Run vision tasks w/ Rockchip chips.
 
||
 
||
 
*
 
*
第202行： 第228行：
 
|Lily
 
|Lily
 
||
 
||
−
* Prepare materials for AnHui
+
* Paper reading
 +
* Organize AI handbook English version course materials
 
||
 
||
 
*
 
*

2025年10月20日 (一) 11:02的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Travel to Zhenjiang
  • AI+ project design
  • AI textbook 2nd semester, primary school version (3 grad)
Lantian Li
  • Review AI Book – College Edition (40/53).
  • Submit Professional title evaluation.
  • Prepare the 1st delivery report for HUAWEI.
Ying Shi
  • prepared for interviews
  • report some experiments on MD tasks
Zhenghai You
  • AATC2025 baseline report in NC
  • Support for the Huawei SS project
  • Midreport
Junming Yuan
  • Evaluating the performance of MT-HuBERT on the speaker diarization task.
    • DER(%)result: MT-HuBERT(3.93) < Cocktail-HuBERT(4.07) < WavLM-BASE(4.55) < MPC-HuBERT(4.83) < HuBERT-BASE(5.88)
  • Start checking the resources for the middle-school AI course with Pengqi and Qiang bro(PPT, teaching plans).
Xiaolou Li
  • Prepared and attended NCMMSC 2025
Zehua Liu
  • VSR topic training for midterm（cer：39% better than 41%）
Pengqi Li
  • Try to Explain for hard-trials(Prof.Li previous work).
  • Outline the paper new structure.
Wan Lin
  • NCMMSC 2025
Tianhao Wang
  • writing paper
  • Midreport
Xiaoxue Luo
  • train of attractor-based speech separation
    • The loss is abnormal, possibly due to the limited distinguishability of the mask, and further adjustments are needed
  • Preparing for my thesis proposal
Junhui Chen
  • Keeps running & debugging reflection metric collection with @ZhangYu
  • Collecting & reading papers from NIPS & COLM 2025
Jiaying Wang
  • convtasnet pit & loudness order exp and visulization analyse
  • mid-term report
    • Report framework diagram
    • Report progress: The first part of the research and the PIT-related experimental section have been completed.
Yu Zhang
  • Training MIC to VPU converter for Huawei AED
  • Keeps running & debugging reflection metric collection with @chenjunhui
Wenqiang Du
  • BUPT anniversary exhibition preparation
  • Check primary AI handbook（done）and related PPT、Jiaoan(6/44)
Yang Wei
  • Fix some bugs of the MD training code. (Not work, bce loss > 0.4)
    • stop inserting special token on phone sequence
    • correct Whisper speech embedding batch mask
    • add segment embedding and separate token embedding to identify the two modality
Yue Gu
  • prepare for the writing test of the civil service exam
  • almost finish the structure of my thesis
Qi Qu
  • Development for elderly alarm customization.
  • Perf test for vision tasks (face detection, face tracking, etc.) across candidate ROS main boards.
  • (In progress) Run vision tasks w/ Rockchip chips.
Lily
  • Paper reading
  • Organize AI handbook English version course materials
取自“http://index.cslt.org/mediawiki/index.php?title=2025-10-20&oldid=43545”