<?xml version="1.0"?>
<?xml-stylesheet type="text/css" href="http://index.cslt.org/mediawiki/skins/common/feed.css?303"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="zh-cn">
		<id>http://index.cslt.org/mediawiki/index.php?action=history&amp;feed=atom&amp;title=14-10-12_Shi_Yin</id>
		<title>14-10-12 Shi Yin - 版本历史</title>
		<link rel="self" type="application/atom+xml" href="http://index.cslt.org/mediawiki/index.php?action=history&amp;feed=atom&amp;title=14-10-12_Shi_Yin"/>
		<link rel="alternate" type="text/html" href="http://index.cslt.org/mediawiki/index.php?title=14-10-12_Shi_Yin&amp;action=history"/>
		<updated>2026-04-09T00:19:48Z</updated>
		<subtitle>本wiki的该页面的版本历史</subtitle>
		<generator>MediaWiki 1.23.3</generator>

	<entry>
		<id>http://index.cslt.org/mediawiki/index.php?title=14-10-12_Shi_Yin&amp;diff=11785&amp;oldid=prev</id>
		<title>Yinshi：以“=== Accomplished this week === * Read and modified the paper of &quot;Noisy Training for Deep Neural Networks in Speech Recognition&quot;. * Prepared for speech group's report...”为内容创建页面</title>
		<link rel="alternate" type="text/html" href="http://index.cslt.org/mediawiki/index.php?title=14-10-12_Shi_Yin&amp;diff=11785&amp;oldid=prev"/>
				<updated>2014-10-14T11:30:37Z</updated>
		
		<summary type="html">&lt;p&gt;以“=== Accomplished this week === * Read and modified the paper of &amp;quot;Noisy Training for Deep Neural Networks in Speech Recognition&amp;quot;. * Prepared for speech group&amp;#039;s report...”为内容创建页面&lt;/p&gt;
&lt;p&gt;&lt;b&gt;新页面&lt;/b&gt;&lt;/p&gt;&lt;div&gt;=== Accomplished this week ===&lt;br /&gt;
* Read and modified the paper of &amp;quot;Noisy Training for Deep Neural Networks in Speech Recognition&amp;quot;.&lt;br /&gt;
* Prepared for speech group's report of &amp;quot;WFST&amp;quot;.&lt;br /&gt;
* Trained a new noisy model for DNN_VAD in multi-silences condition.&lt;br /&gt;
&lt;br /&gt;
=== Next Week ===&lt;br /&gt;
* Submit the paper of &amp;quot;Noisy Training for Deep Neural Networks in Speech Recognition&amp;quot;.&lt;br /&gt;
* Test the performance of new DNN_VAD model in multi-silences condition.&lt;br /&gt;
* Try to merge the sil-pdf for DNN_VAD.&lt;br /&gt;
* Find the bug for DNN_VAD under the condition of 2-classes.&lt;br /&gt;
* Fix the bug for DNN_VAD under the condition of 2-classes.&lt;br /&gt;
* Test the performance for 2-classes noisy model in puchar's VAD framework.&lt;br /&gt;
* Continue to test the other methods for ROS.&lt;br /&gt;
* Continue to test for low-scale-language-train.&lt;/div&gt;</summary>
		<author><name>Yinshi</name></author>	</entry>

	</feed>