|
|
| 第30行： |
第30行： |
| | |Zhiyuan Tang | | |Zhiyuan Tang |
| | || | | || |
| − | * | + | * Adaptation with nf-dt asr. |
| | || | | || |
| − | * | + | * Continue. |
| | || | | || |
| | * | | * |
| People |
This Week |
Next Week |
Task Tracking (DeadLine)
|
| Dong Wang
|
- More investigation on Maximum Gaussianlity training
- Reformulate the TASLP paper
|
- Complete the MG paper
- Start working on the condition transfer (CT) paper
|
|
| Yunqi Cai
|
|
|
|
| Zhiyuan Tang
|
- Adaptation with nf-dt asr.
|
|
|
| Lantian Li
|
- Compare two MLE methods.
- Length norm and whitening in NL scoring.
|
|
|
| Ying Shi
|
- sub space with trainable mean of r code
- sub space flow with gauss. mixture r code
|
- analysis the gaussianlity of r space
- verify the robustness of sub space flow
|
|
| Haoran Sun
|
- Analysed latent space of ML-DNF
- Classification via logpz
|
- Analysises of subspace DNF
|
|
| Yue Fan
|
|
|
|
| Jiawen Kang
|
- Read NDA papers;
- MAML code;
- MAML experiments.
|
- MAML SSMC&MC experiments.
|
|
| Ruiqi Liu
|
- revise the paper draft.
- Multi-genre generalization.
- MC experiments data.
|
|
|
| Haolin Chen
|
- Subspace Flow
- Noisy r var=1, fixed mean
- GMM Loss
|
- Subspace Flow
- Other noise
- Improve performance
|
|
