| People |
Last Week |
This Week |
Task Tracking (DeadLine)
|
| Yibo Liu
|
- Reconstructed the model on pytorch.
|
- 1.Tune the parameters and train a model with good results.
- 2.Add planning and polishing procedure.
|
|
| Xiuqi Jiang
|
- Reproducing the planning part and provide a simple framework of planning procedure.
|
- Post polishing still remains to be finished.
|
|
| Jiayao Wu
|
- finished several experiments on node-sparseness
|
- keep on doing experiments
|
|
| Zhaodi Qi
|
|
- improve the system ，because the results is bad.
|
|
| Jiawei Yu
|
- Familiar with the code of attention experiment.
- Modify the code to achieve phonetic attention.
|
- finish the phonetic attention experiment.
|
|
| Yunqi Cai
|
- 1,use the ASR test_data set ref.txt to test the original bert and then compare with the fine-tuned Bert.
- 2,compare the difference between hyp.text which comes from ASR test results, and investigate how to mask the error in the sentence of the ASR result.
- 3,set a rule among all the result(hyp.text) to find out the error to be masked.
|
|
|
| Dan He
|
|
- Continue to study the time complexity of TT-decomposition
|
|
| Yang Zhang
|
|
- did some experiments in mnist dataset
|
|
| Wenwei Dong
|
- ivector+fbank as feature compare with fbank in GOP
|
- read papers, find some new speaker adaptation methods
|
|
