“Zhiyuan Tang 2016-05-30”版本间的差异
来自cslt Wiki
| 第4行： | 第4行： | ||
1. all partial models will be generated in one day, more results in[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=515], | 1. all partial models will be generated in one day, more results in[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=515], | ||
| + | |||
conclusion: | conclusion: | ||
Enhancing on the part of spk seems not help speech while enhancing speech helps spk. | Enhancing on the part of spk seems not help speech while enhancing speech helps spk. | ||
It's consistent with that for partial when data for spk increases and data for speech keeps the same, speech performs worse while | It's consistent with that for partial when data for spk increases and data for speech keeps the same, speech performs worse while | ||
spk becomes better. | spk becomes better. | ||
| + | |||
| + | Bast on wsj_test and eval2000, vad is important for baseline sre, while for joint, no vad or lower threshold for vad are better. | ||
| + | |||
2. bilingual, results in[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]; | 2. bilingual, results in[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=536]; | ||
| + | |||
2016年5月30日 (一) 00:57的版本
Last week:
1. all partial models will be generated in one day, more results in[1],
conclusion: Enhancing on the part of spk seems not help speech while enhancing speech helps spk. It's consistent with that for partial when data for spk increases and data for speech keeps the same, speech performs worse while spk becomes better.
Bast on wsj_test and eval2000, vad is important for baseline sre, while for joint, no vad or lower threshold for vad are better.
2. bilingual, results in[2];
This week:
1. more improvement on bilingual, such as p+r as interaction info;
2. paper initialization for joint training of journal version.
