“Lantian Li 2016-08-22”版本间的差异
来自cslt Wiki
| 第3行： | 第3行： | ||
:* OLE evaluation task. -- Done | :* OLE evaluation task. -- Done | ||
| − | :* Deep speaker embedding (Random sample training). | + | :* Deep speaker embedding ( Random sample training RST ). |
::* Make the d-vector baseline on Theano. | ::* Make the d-vector baseline on Theano. | ||
| 第9行： | 第9行： | ||
:* Local training. | :* Local training. | ||
| − | + | ::* Data preparation -- Done. | |
| − | + | ::* T-matrix training. | |
:* Deep speaker embedding ( LSTM + LR/Margin ) -- hold. | :* Deep speaker embedding ( LSTM + LR/Margin ) -- hold. | ||
| 第17行： | 第17行： | ||
* This Week | * This Week | ||
| − | :* Go on | + | :* Go on 'Random sample training' and `Local training tasks'. |
2016年8月22日 (一) 03:39的版本
- Weekly Report
- OLE evaluation task. -- Done
- Deep speaker embedding ( Random sample training RST ).
- Make the d-vector baseline on Theano.
- Local training.
- Data preparation -- Done.
- T-matrix training.
- Deep speaker embedding ( LSTM + LR/Margin ) -- hold.
- This Week
- Go on 'Random sample training' and `Local training tasks'.
