“Zhiyuan Tang 2015-12-07”版本间的差异
来自cslt Wiki
| 第2行： | 第2行： | ||
Last week: | Last week: | ||
| + | 1. launched experiments on 1400h-Chinese with CTC/nnet3/Kaldi; | ||
| + | 2. verified the code for conditioning learning of dnn. | ||
| + | |||
| + | |||
| + | This week: | ||
| + | |||
| + | 1. more research about ctc/nnet3; | ||
| + | |||
| + | 2. find the reason why language vector doesn't help; | ||
| + | |||
| + | 3. something about Memory net. | ||
| 第8行： | 第19行： | ||
==== End-to-End ==== | ==== End-to-End ==== | ||
*monophone ASR --Zhiyuan | *monophone ASR --Zhiyuan | ||
| − | :* MPE | + | :*MPE |
| − | :* CTC/nnet3/Kaldi | + | :*CTC/nnet3/Kaldi |
| − | + | === conditioning learning === | |
* language vector into multiple layers --zhiyuan | * language vector into multiple layers --zhiyuan | ||
:* a Chinese paper | :* a Chinese paper | ||
* speech rate into multiple layers --zhiyuan | * speech rate into multiple layers --zhiyuan | ||
:*verify the code for extra input(s) into DNN | :*verify the code for extra input(s) into DNN | ||
2015年12月7日 (一) 06:34的版本
Last week:
1. launched experiments on 1400h-Chinese with CTC/nnet3/Kaldi;
2. verified the code for conditioning learning of dnn.
This week:
1. more research about ctc/nnet3;
2. find the reason why language vector doesn't help;
3. something about Memory net.
End-to-End
- monophone ASR --Zhiyuan
- MPE
- CTC/nnet3/Kaldi
conditioning learning
- language vector into multiple layers --zhiyuan
- a Chinese paper
- speech rate into multiple layers --zhiyuan
- verify the code for extra input(s) into DNN
