|
|
| （相同用户的3个中间修订版本未显示） |
| 第30行： |
第30行： |
| | |Yixiang Chen | | |Yixiang Chen |
| | || | | || |
| − | * Because of illness only wrote book and read paper | + | * Read paper and learning joint learning configuration |
| | + | * Write the ML-book. |
| | || | | || |
| − | * In order to improve the replay task to Modify the MFCC calculation | + | * Complete ML-book. |
| | |- | | |- |
| | | | |
| 第41行： |
第42行： |
| | |Lantian Li | | |Lantian Li |
| | || | | || |
| − | * | + | * Joint-training on TASLP (speaker parts). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=573] |
| | || | | || |
| − | * | + | * Complete the additional experiments on TASLP-speaker parts |
| | |- | | |- |
| | | | |
| Date |
People |
Last Week |
This Week
|
| 2016.11.07
|
Hang Luo
|
- make a report of 2 Inter Speech papers
- run joint training experiments and the result is [1]
|
- read papers about highway connection and multi-task.
|
| Ying Shi
|
- paper reading kazak speech recognition data prep
|
- baseline of kazak speech recoginition
|
| Yixiang Chen
|
- Read paper and learning joint learning configuration
- Write the ML-book.
|
|
| Lantian Li
|
- Joint-training on TASLP (speaker parts). [2]
|
- Complete the additional experiments on TASLP-speaker parts
|
| Zhiyuan Tang
|
- almost finished the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[3].
|
- report for Weekly Reading;
- joint training for bilingual.
|
| Date |
People |
Last Week |
This Week
|
| 2016.10.31
|
Hang Luo
|
- Know the source code of joint training.
- Experiments on joint training, change the receive computation blocks and try non-symmetric structure.The result expected on this Thursday.
|
- Find paper about joint training to read.
- Try new experiments according to last two experiments.
|
| Ying Shi
|
- DNN and TDNN visualization;CNN baseline(th30) new model DNN+lstm(th30);ML-book slide
|
- ML-book continue DNN visualization maybe I should find a new tool t-sne is not powerful enough
|
| Yixiang Chen
|
- Joint-training (GMM baseline)
|
|
| Lantian Li
|
- Joint-training on TASLP (DNN i-vector parts). [4]
- Joint-training on SRE and LRE (Neural model is over-fitting...). [5]
|
- Joint-training on TASLP.
- Joint-training on SRE and LRE.
|
| Zhiyuan Tang
|
|
- report for Weekly Reading;
- finish the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[6].
|
