“Zhiyong Zhang”版本间的差异
来自cslt Wiki
（→Summary） |
|||
| 第5行： | 第5行： | ||
Priority | Tasks name | Status | Notions | Priority | Tasks name | Status | Notions | ||
-------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ||
| − | 1 | Bi-Softmax | | + | 1 | Bi-Softmax | ■■■□□□□□□□ | 1400h am training and problem fixing |
-------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ||
2 | RNN+DAE | □□□□□□□□□□ | | 2 | RNN+DAE | □□□□□□□□□□ | | ||
2015年1月10日 (六) 01:50的版本
目录
Task schedules
Summary
--------------------------------------------------------------------------------------------------------
Priority | Tasks name | Status | Notions
--------------------------------------------------------------------------------------------------------
1 | Bi-Softmax | ■■■□□□□□□□ | 1400h am training and problem fixing
--------------------------------------------------------------------------------------------------------
2 | RNN+DAE | □□□□□□□□□□ |
--------------------------------------------------------------------------------------------------------
Speech Recognition
Multi-lingual Am training
Bi-Softmax
- Using two distinct softmax for English and Chinese data.
- Testing on 100h-Ch+100h-En, better performance observed.
- Now testing the source code on 1400h_8k data, but stange decoding results got.Need to further investigate.
Papers To Read
- 1, Learned-Norm pooling for deep feedforward and recurrent neural networks
