“2025-06-30”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第53行: 第53行:
 
||
 
||
 
* MT-HuBERT paper(80%)
 
* MT-HuBERT paper(80%)
* Middle-school AI handbook
+
* Middle-school AI Textbook
 
||
 
||
 
*
 
*
第87行: 第87行:
 
||
 
||
 
* Prepare for the Tsinghua Middle School AI Summer School
 
* Prepare for the Tsinghua Middle School AI Summer School
* High-school AI handbook
+
* High-school AI Textbook
 
||
 
||
 
*
 
*

2025年6月30日 (一) 10:49的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Textbook composition
Lantian Li
  • Write ML book (56/326)
  • Go on Hainan D&B Course
Ying Shi
  • keep working on my thesis
Zhenghai You
  • AATC2025 Baseline (SI-SDR 0.51)
Junming Yuan
  • MT-HuBERT paper(80%)
  • Middle-school AI Textbook
Xiaolou Li
  • CNVSRC2025 Baseline
Zehua Liu
  • CNVSRC2025 Baseline code, website document and so on
Pengqi Li
  • Prepare for the Tsinghua Middle School AI Summer School
  • High-school AI Textbook
Wan Lin
  • Supply experiments for paper
  • Run some experiments(self att mask for test in multi-layer and leverage 1-layer feature extractor for 8-layer)
  • Paper: Revision parts mentioned are nearly finished, need further check
Tianhao Wang
  • Huawei competition baseline data preparation
Xiaoxue Luo
  • Huawei competition things
Junhui Chen
  • Finished Hainan teaching assistant work
  • Continue revising NS paper
  • Read paper
Jiaying Wang
  • GuoChuang Competition
    • modify slides v2 and verbatim transcript
    • LingAn bank account already opened
  • Prepare Libri2Mix - Libri5Mix for ASR
Yu Zhang
Wenqiang Du
  • Write and revise AI courses draft from Jiaoyubu (5,7,8)
  • Revise Primary school AI book(4 and 5 grade)
  • Prepare 11000 hours of data to Wei(for big text enroll model)
Yang Wei
  • Adapt the AM for mispronounce detection with child data
  • Start to train text enroll kws model with 11000 hours data
Yue Gu
  • almost finish th supplement of experiments
  • rewriting a section to make it more clear
Qi Qu
  • (Continuous) integrating PJSIP to ESP32-based application.
  • Experiment: Text-Enroll KWS + FunASR [1].