“Lantian Li 2016-08-22”版本间的差异
来自cslt Wiki
（以“* Weekly Report :* Deep speaker embedding (Random sample training). :* Deep speaker embedding ( LSTM + LR/Margin ) -- hold. :* OLE evaluation task. * This Wee...”为内容创建页面） |
|||
| 第1行： | 第1行： | ||
* Weekly Report | * Weekly Report | ||
| + | |||
| + | :* OLE evaluation task. -- Done | ||
:* Deep speaker embedding (Random sample training). | :* Deep speaker embedding (Random sample training). | ||
| + | Make the d-vector baseline on Theano. | ||
| − | + | :* Local training. | |
| − | :* | + | |
| − | :* | + | Data preparation -- Done. |
| + | |||
| + | T-matrix training. | ||
| + | |||
| + | :* Deep speaker embedding ( LSTM + LR/Margin ) -- hold. | ||
* This Week | * This Week | ||
:* Go on three tasks. | :* Go on three tasks. | ||
2016年8月22日 (一) 03:37的版本
- Weekly Report
- OLE evaluation task. -- Done
- Deep speaker embedding (Random sample training).
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 three tasks.
