“Zhiyuan Tang 2015-12-07”版本间的差异
来自cslt Wiki
| 第4行： | 第4行： | ||
1. launched experiments on 1400h-Chinese with CTC/nnet3/Kaldi; | 1. launched experiments on 1400h-Chinese with CTC/nnet3/Kaldi; | ||
| − | 2. verified the code for conditioning learning of dnn. | + | 2. verified the code for conditioning learning of dnn using speech rate as extra input(s), results in [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=480]; |
| 第17行： | 第17行： | ||
| − | ==== End-to-End ==== | + | |
| + | |||
| + | ==TASKS== | ||
| + | ====== End-to-End ====== | ||
*monophone ASR --Zhiyuan | *monophone ASR --Zhiyuan | ||
:*MPE | :*MPE | ||
:*CTC/nnet3/Kaldi | :*CTC/nnet3/Kaldi | ||
| − | + | ===== conditioning learning ===== | |
| − | === 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) 06:56的版本
Last week:
1. launched experiments on 1400h-Chinese with CTC/nnet3/Kaldi;
2. verified the code for conditioning learning of dnn using speech rate as extra input(s), results in [1];
This week:
1. more research about ctc/nnet3;
2. find the reason why language vector doesn't help;
3. something about Memory net.
TASKS
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
