|
|
| 第219行： |
第219行： |
| | |Qi Qu | | |Qi Qu |
| | || | | || |
| − | * | + | * KWS: |
| | + | ** Cantonese train dataset collected and annotated: ~200 speakers, 10 keywords, 10 repeats per keyword. |
| | + | ** More scene-specific test dataset collected: school, meeting, exhibition, etc. |
| | + | ** Locating ideal keyword-wise thresholds for specific scenes using DCF (detection cost function). |
| | || | | || |
| | * | | * |
| People |
This Week |
Next Week |
Task Tracking (DeadLine)
|
| Dong Wang
|
- Middle School AI book v0.0
|
|
|
| Lantian Li
|
- GPU status [1]
- Apply for the AP title (Failed)
- Submit two undergraduate thesis projects
|
|
|
| Ying Shi
|
|
|
|
| Zhenghai You
|
- ICASSP exp and paper writing[2]
|
|
|
| Junming Yuan
|
- mixed Hubert pretraining v1 (in progress)
|
|
|
| Xiaolou Li
|
|
|
|
| Zehua Liu
|
- CNVSRC 2024 Website Finish
- ICASSP exp and paper writing[3]
|
|
|
| Pengqi Li
|
- [4]Pondering the expected conclusions for paper
- Experiment on timit(Finding and disadvantage)
- poor consistency of TAO and LayerCAM methods
- Toy Experiment
- Challenge: Do the conclusions drawn from SID tasks (toy experiments) align with those from SV tasks (more SOTA models)?
|
- To investigate and reproduce existing interpretability methods for verification task.
- To analyze the importance of phones using TTS datasets(broad coverage of phonemes) based SOTA models
|
|
| Wan Lin
|
|
|
|
| Tianhao Wang
|
|
|
|
| Zhenyu Zhou
|
- check the conditional chain code
|
|
|
| Junhui Chen
|
- Writing Neural Scoring paper, 1st ver. done.
|
|
|
| Jiaying Wang
|
|
|
|
| Yu Zhang
|
- reproduce iTransformer
- Transfer iTrasnformer to financial data[5]
|
|
|
| Wenqiang Du
|
- Write middle school handbook(completed)
- Continue to training Chinese and Cantonese KWS model
|
|
|
| Yang Wei
|
- Get familiar with text enroll KWS training
|
|
|
| Lily
|
|
|
|
| Turi
|
- Working on dataset paper refinement & additional experiment
- Attempting using pretrained model, not successful yet
|
|
|
| Yue Gu
|
|
|
|
| Qi Qu
|
- KWS:
- Cantonese train dataset collected and annotated: ~200 speakers, 10 keywords, 10 repeats per keyword.
- More scene-specific test dataset collected: school, meeting, exhibition, etc.
- Locating ideal keyword-wise thresholds for specific scenes using DCF (detection cost function).
|
|
|
