“Zhiyuan Tang 2016-04-18”版本间的差异
来自cslt Wiki
（以“ Last week: 1. enhancing the joint model with SWBD focusing on speech recognition, shows improvement[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=...”为内容创建页面） |
|||
| 第5行： | 第5行： | ||
1. enhancing the joint model with SWBD focusing on speech recognition, shows improvement[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=515]; | 1. enhancing the joint model with SWBD focusing on speech recognition, shows improvement[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=515]; | ||
| − | 2. problem remains that when the WSJ was reduced to be 8k, the advantage of joint training disappeared. | + | 2. problem remains that when the WSJ was reduced to be 8k, the advantage of joint training disappeared at least for speech recognition. |
2016年4月18日 (一) 00:48的版本
Last week:
1. enhancing the joint model with SWBD focusing on speech recognition, shows improvement[1];
2. problem remains that when the WSJ was reduced to be 8k, the advantage of joint training disappeared at least for speech recognition.
This week:
1. find the reason why joint training failed on 8k WSJ;
2. following ICASSP 16.
