“Lantian Li 2016-08-22”版本间的差异
来自cslt Wiki
| （相同用户的4个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
* Weekly Report | * Weekly Report | ||
| − | :* OLE evaluation task. -- Done | + | :* APSIPA 2016 OLE evaluation task. -- Done |
:* Deep speaker embedding ( Random sample training RST ). | :* Deep speaker embedding ( Random sample training RST ). | ||
| − | ::* Make the d-vector baseline on Theano. | + | ::* Make the d-vector baseline on Theano. -- Done |
| + | |||
| + | ::* Prepare the RST codes on Theano. | ||
:* Local training. | :* Local training. | ||
| 第14行： | 第16行： | ||
:* Deep speaker embedding ( LSTM + LR/Margin ) -- hold. | :* Deep speaker embedding ( LSTM + LR/Margin ) -- hold. | ||
| + | |||
| + | :* Yixiang's daily reports. [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Yixiang_Chen here]. | ||
* This Week | * This Week | ||
| − | :* Go on 'Random sample training' and | + | :* Go on 'Random sample training' and 'Local training tasks'. |
2016年8月22日 (一) 03:43的最后版本
- Weekly Report
- APSIPA 2016 OLE evaluation task. -- Done
- Deep speaker embedding ( Random sample training RST ).
- Make the d-vector baseline on Theano. -- Done
- Prepare the RST codes on Theano.
- Local training.
- Data preparation -- Done.
- T-matrix training.
- Deep speaker embedding ( LSTM + LR/Margin ) -- hold.
- Yixiang's daily reports. here.
- This Week
- Go on 'Random sample training' and 'Local training tasks'.
