“2025-10-13”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（4位用户的5个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
*  
+
* AI book (primary) English version done
 +
* AI textbook (2nd semester) Grad 3 (1/2)
  
 
||
 
||
第45行： 第46行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*  
+
* SS 3-5mix benchmark for Huawei Project
 +
* Multi-Step Infer[https://z1et6d3xtb.feishu.cn/docx/LlgjdMYVbocGD1xjkMSc17Ttnke]
 +
** Multi-task-search can keep reference metrics on 2-mix data while improving non reference metrics
 +
** However, on noisy data, our method is not effective, maybe the quality of speech extraction is too poor, exceeding threshold to improve
 
||
 
||
 
*
 
*
第67行： 第71行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*  
+
* avhubert pretraining iter3 and finetune test
 +
* orgnize collected data
 +
* do some prepare for NCMMSC2025
 
||
 
||
 
*  
 
*  
第78行： 第84行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
* LLM to Generate topics as context For midterm thesis
 +
* stuff about CNVSRC2025
 
||
 
||
 
*
 
*
第100行： 第107行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*  
+
* Experiments for memory and reasoning [https://z1et6d3xtb.feishu.cn/wiki/NJLtw3l1Xi2xQBkUpCbcRic9nOh?from=from_copylink]
 +
* Start reviewing and reproducing weixiong's code
 
||
 
||
 
*
 
*
第147行： 第155行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* separation training
 +
** 3mix cc and cc-order use loud data
 +
** 4mix pit and pit-order use loud data
 +
** 2-5mix cc training code finished
 +
* spk model
 +
** change structure to ResNet34 (wait to train)
 
||
 
||
 
*
 
*

2025年10月13日 (一) 10:58的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • AI book (primary) English version done
  • AI textbook (2nd semester) Grad 3 (1/2)
Lantian Li
  • Review AI Book — College Edition (34/53).
  • My professional title evaluation (1/2).
  • Proposal for audio scene detection.
Ying Shi
  • submitted resumes to many companies
  • prepared for interviews
  • conducted some preliminary experiments on MD tasks
Zhenghai You
  • SS 3-5mix benchmark for Huawei Project
  • Multi-Step Infer[1]
    • Multi-task-search can keep reference metrics on 2-mix data while improving non reference metrics
    • However, on noisy data, our method is not effective, maybe the quality of speech extraction is too poor, exceeding threshold to improve
Junming Yuan
  • Further evaluation of our MT-HuBERT model on 2 speech generation downstream tasks(SS & SE).
    • Result in [2]
Xiaolou Li
  • avhubert pretraining iter3 and finetune test
  • orgnize collected data
  • do some prepare for NCMMSC2025
Zehua Liu
  • LLM to Generate topics as context For midterm thesis
  • stuff about CNVSRC2025
Pengqi Li
Wan Lin
  • Experiments for memory and reasoning [3]
  • Start reviewing and reproducing weixiong's code
Tianhao Wang
  • writing my paper
  • add a multi-modal query baseline
Xiaoxue Luo
  • paper sharing
  • prepare the code of attractor-based speech separation, the model is in training
Junhui Chen
  • collect more novel reflection method metrics for analysis
  • paper reading about LM swarm
Jiaying Wang
  • separation training
    • 3mix cc and cc-order use loud data
    • 4mix pit and pit-order use loud data
    • 2-5mix cc training code finished
  • spk model
    • change structure to ResNet34 (wait to train)
Yu Zhang
  • paper reading and prepare for paper sharing
  • AED: add pitch dim training & test (no significant improvement)
Wenqiang Du
  • Check english version AI primary handbook
  • Dealing with our company accounting issues
Yang Wei
  • Debug training problem of MD model on TIMIT
Yue Gu
  • submit resume and prepare for the job interview
  • SPL paper revision and proof
  • my PhD thesis
Qi Qu
  • Misc. tech support for Babel Technology.
Lily
  • Thesis Writing
  • AIRadiance dailywork
取自“http://index.cslt.org/mediawiki/index.php?title=2025-10-13&oldid=43520”