“Zhiyong Zhang”版本间的差异
来自cslt Wiki
| 第22行： | 第22行： | ||
* Testing on 100h-Ch+100h-En, better performance observed. | * 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. | * Now testing the source code on 1400h_8k data, but stange decoding results got.Need to further investigate. | ||
| + | |||
| + | =Reading Lists= | ||
| + | *[[Speech Group Reading|张之勇 2014-12-28 APSIPA paper reading]] | ||
2015年10月29日 (四) 07:08的版本
目录
Papers To Read
- 1, Learned-Norm pooling for deep feedforward and recurrent neural networks
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.
