“2025-04-07”版本间的差异

• Submit AI Handbook (College Edition) (10/10)

• Huawei project cooperation
• thesis

• Some tests on the second iteration model of Huawei TSE project
• Revised rebuttal

• some works with brother Qiang:
  • Review primary school PPT
  • Make some PPTs
• some AI practice handbook works

• Reproduction of ASR component in LipVoicer. Finetuning a new pre-trained Mandarin ASR system is challenging due to the complexity of integrating diffusion steps (or diffusion steps embedding) into a new ASR architecture. Therefore, finetuning the existing checkpoint that was pretrained on English will be a more practical approach.

• Finish reproduction in Wed.
• Start to audit new 3000 hours data.

• Finish Lip2Speech model Training(Need Vocoder to reconstruct)
• IS25 Rebutall

• Some(3) PPTs development

• Huawei project things

• did some testing work of sound separation

• Do some mid-term course homework things
• read paper

Multi Agent Investment: long term investment seems useful (better than pervious short term only investment), but still not good than buy and hold baseline

• Policy Level Problem:
  • feedback is portfolio level (about to choose which portfolio), need to design stock level feedback.
  • The current investment strategy group's strategy generation process is too simplistic and needs to incorporate additional reasoning pipelines.
• Group Level Prombel:
  • weight average of different policy instead of choose one from them.

• Test text enroll kws model with southern accent data [1]

• move my code, model and training envs to new cloud service, reproduce some exps
• read several papers and write the question analysis paragraph

• Reorganizing codebase for evaluating KWS models (audio-enroll and text-enroll).