<?xml version="1.0"?>
<?xml-stylesheet type="text/css" href="http://www.cslt.org/mediawiki/skins/common/feed.css?303"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="zh-cn">
		<id>http://www.cslt.org/mediawiki/index.php?action=history&amp;feed=atom&amp;title=140901_-_Shi_Yin</id>
		<title>140901 - Shi Yin - 版本历史</title>
		<link rel="self" type="application/atom+xml" href="http://www.cslt.org/mediawiki/index.php?action=history&amp;feed=atom&amp;title=140901_-_Shi_Yin"/>
		<link rel="alternate" type="text/html" href="http://www.cslt.org/mediawiki/index.php?title=140901_-_Shi_Yin&amp;action=history"/>
		<updated>2026-04-03T20:27:37Z</updated>
		<subtitle>本wiki的该页面的版本历史</subtitle>
		<generator>MediaWiki 1.23.3</generator>

	<entry>
		<id>http://www.cslt.org/mediawiki/index.php?title=140901_-_Shi_Yin&amp;diff=10866&amp;oldid=prev</id>
		<title>Yinshi：以内容“=== Accomplished this week === * Found the bug for noisy-training and re-trained the error model. * Decoded on the right model and trained two new models such as white/...”创建新页面</title>
		<link rel="alternate" type="text/html" href="http://www.cslt.org/mediawiki/index.php?title=140901_-_Shi_Yin&amp;diff=10866&amp;oldid=prev"/>
				<updated>2014-09-01T12:26:51Z</updated>
		
		<summary type="html">&lt;p&gt;以内容“=== Accomplished this week === * Found the bug for noisy-training and re-trained the error model. * Decoded on the right model and trained two new models such as white/...”创建新页面&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;
* Found the bug for noisy-training and re-trained the error model.&lt;br /&gt;
* Decoded on the right model and trained two new models such as white/cafe/clean 15_1 &amp;amp; white/cafe/clean 15_0.1.&lt;br /&gt;
* Decoded on the speech-rate model with different data and analyzed the result.&lt;br /&gt;
* Tested dnn_vad on various database and analyzed the distributions about training data and evaluation data.&lt;br /&gt;
&lt;br /&gt;
=== Next Week ===&lt;br /&gt;
* Getting the results for new noisy models.&lt;br /&gt;
* Checking the labels of database for dnn_vad.&lt;br /&gt;
* Training the noisy model for dnn_vad.&lt;br /&gt;
* Extracting speech data of different ROS, construct a new test set.&lt;br /&gt;
* Try to remove silence when compute ROS.&lt;/div&gt;</summary>
		<author><name>Yinshi</name></author>	</entry>

	</feed>