http://www.cslt.org/mediawiki/index.php?action=history&feed=atom&title=Zhiyuan_Tang_2015-09-28Zhiyuan Tang 2015-09-28 - 版本历史2026-04-04T02:49:39Z本wiki的该页面的版本历史MediaWiki 1.23.3http://www.cslt.org/mediawiki/index.php?title=Zhiyuan_Tang_2015-09-28&diff=16944&oldid=prevTangzy：以“ Last week: 1. when changing the halving_factor from 0.5 to 0.7 for end-to-end ASR, the results seem not better; 2. nnet learning from i-vector worked not well;...”为内容创建页面2015-09-28T13:39:12Z<p>以“ Last week: 1. when changing the halving_factor from 0.5 to 0.7 for end-to-end ASR, the results seem not better; 2. nnet learning from i-vector worked not well;...”为内容创建页面</p>
<p><b>新页面</b></p><div><br />
Last week: <br />
<br />
1. when changing the halving_factor from 0.5 to 0.7 for end-to-end ASR, the results seem not better; <br />
<br />
2. nnet learning from i-vector worked not well;<br />
<br />
3. some coding for nnet with metric loss function, not realised. <br />
<br />
<br />
This week: <br />
<br />
more about nnet learning from i-vector and nnet with metric loss function, CNN should be considered.</div>Tangzy