“2025-03-24”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第43行： 第43行：
 
||
 
||
 
* Complete some tests required by Huawei[https://z1et6d3xtb.feishu.cn/wiki/OXubwl2fIip91vkYsgMc1duhnLd]
 
* Complete some tests required by Huawei[https://z1et6d3xtb.feishu.cn/wiki/OXubwl2fIip91vkYsgMc1duhnLd]
 +
* Starting to implement TSE diffusion refiner, and plan to share some papers on speech separation and speech enhancement refiner on Friday
 
||
 
||
 
*
 
*

2025年3月24日 (一) 10:55的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
Lantian Li
  • lots of paperwork and staffwork
Ying Shi
  • revisit cohort conditional chain overlap asr and conduct experiments (model is in training)
  • thesis
Zhenghai You
  • Complete some tests required by Huawei[1]
  • Starting to implement TSE diffusion refiner, and plan to share some papers on speech separation and speech enhancement refiner on Friday
Junming Yuan
  • Rewrite MT-HuBERT paper (1/5)
  • AI practice handbook design of primary school and middle school(contents finished)
Xiaolou Li
  • VSR big data training (5500h) and debug
  • Reproducing LipVoicer on Mandarin (overfitting now, still finding the best hyperparameter)
  • Writing the VTS test document
Zehua Liu
  • GA VTS test document writing
  • VTS paper Reading and Sharing this Friday
Pengqi Li
  • Prepare the AI course for Tsinghua University middle School.
  • write paper for "Design course"
Wan Lin
  • run ablation experiments [2]
Tianhao Wang
  • dragon05 data transfer
  • 4-mix & 5-mix training
  • huawei project things
Xiaoxue Luo
  • Sound separation
    • baseline: there are some bugs in previous code that resulting in low test results, so I modified the code and retrained it
  • filter testing data for Huawei project
Zhenyu Zhou
Junhui Chen
  • improve code efficiency, continue to test diarization on vox-e
  • read paper
Jiaying Wang
  • finish model structure
  • current problem：ctc loss Nan
    • data-related reason of NaN have been fixed, and further investigation is ongoing
Yu Zhang
Wenqiang Du
  • Summit AI primary handbook
  • AI primary handbook's PPT (44/44),Need to Check
  • Check AI middl handbook(108/278)
Yang Wei
  • Text enroll kws model adaptation with keyword phone label from decoding and non-linear adaptation layer. (in progress)
Turi
  • Completed writing thesis (Will revise this week)
Yue Gu
  • FIP-based personality-gated adaptation with synthetic data for personal ASR, almost finish preview evaluation exps.
  • read 2 TTS-augment papers and reivew an interspeech2025 paper
Qi Qu
  • Text-enroll KWS: different window shifts (e.g. one at 100ms and the other at 200ms) for different keywords.
  • VPR experiment: finding suitable thresholds for defined use cases.
取自“http://index.cslt.org/mediawiki/index.php?title=2025-03-24&oldid=42952”