“Zhiyuan Tang 2015-12-14”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
第2行: 第2行:
 
Last week:
 
Last week:
  
1. launched experiments on 1400h-Chinese plus 100h English with CTC/nnet3/Kaldi, it's much faster than those on train97 as it's on train88 with 8 jobs parallel;
+
1. launched experiments on 1400h-Chinese plus 100h English with CTC/nnet3/Kaldi, it's much faster than those on train97 with 4 jobs parallel as it's on train88 with 8;
  
 
2. got refered ruselts of Kaldi/CTC on 1400h-Chinese[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=492];
 
2. got refered ruselts of Kaldi/CTC on 1400h-Chinese[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=492];

2015年12月14日 (一) 00:57的最后版本

Last week:

1. launched experiments on 1400h-Chinese plus 100h English with CTC/nnet3/Kaldi, it's much faster than those on train97 with 4 jobs parallel as it's on train88 with 8;

2. got refered ruselts of Kaldi/CTC on 1400h-Chinese[1];

3. turned to SPEAKER.


This week:

1. more research about SPEAKER;

2. supervise the experiments;

3. reading.


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