“Zhiyong Zhang”版本间的差异
来自cslt Wiki
（→Task schedule） |
|||
| 第1行： | 第1行： | ||
| − | ==Task | + | ==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. | ||
==To Do== | ==To Do== | ||
===Papers To Read === | ===Papers To Read === | ||
2015年1月7日 (三) 00:57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.
