“2026-01-26”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第133行： 第133行：
 
||
 
||
 
*
 
*
 +
||
 +
*
 +
||
 +
*
 +
|-
 +
 +
 +
|-
 +
|Xiaoxue Luo
 +
||
 +
* prepare 2mix speech separation results for ASR test
 +
* 2-5mix multi_head separation model for Huawei project
 +
** data: remove data that the target audio is mixed audio(input equals output, model does not learn)
 +
** loss: add MSE_loss to the original SISDR_loss to control the energy amplitude of output audio
 
||
 
||
 
*
 
*

2026年1月26日 (一) 10:15的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
Lantian Li
  • Recheck AI textbooks for senior middle school.
  • MoE daily work (busy week)
  • Go on the final review of my MLA book (6/10)
Wenqiang Du
Yang Wei
Ying Shi
Yue Gu
  • write my thesis
Lily
Pengqi Li
Junming Yuan
Yu Zhang
Junhui Chen
  • (caught a cold)
  • MMLU
    • difference in the ECS distribution between good nodes and bad nodes.
    • metrics loss helps select high-quality nodes and eliminate low-quality ones. [1]
Jiaying Wang
Xiaoxue Luo
  • prepare 2mix speech separation results for ASR test
  • 2-5mix multi_head separation model for Huawei project
    • data: remove data that the target audio is mixed audio(input equals output, model does not learn)
    • loss: add MSE_loss to the original SISDR_loss to control the energy amplitude of output audio
Bochao Hu
Hongcheng Zhang
Weiman Sun
取自“http://www.cslt.org/mediawiki/index.php?title=2026-01-26&oldid=43896”