<?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=140623_-_Shi_Yin</id>
		<title>140623 - 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=140623_-_Shi_Yin"/>
		<link rel="alternate" type="text/html" href="http://index.cslt.org/mediawiki/index.php?title=140623_-_Shi_Yin&amp;action=history"/>
		<updated>2026-04-13T19:22:33Z</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=140623_-_Shi_Yin&amp;diff=10276&amp;oldid=prev</id>
		<title>Yinshi：以内容“=== Accomplished this week === * Tested the 4*600+800 model + 150k / 20k / 10k / 5k graph + new 1e-7 with biglm mode. * Get the wer &amp; RT respectively. * Fixed the error...”创建新页面</title>
		<link rel="alternate" type="text/html" href="http://index.cslt.org/mediawiki/index.php?title=140623_-_Shi_Yin&amp;diff=10276&amp;oldid=prev"/>
				<updated>2014-06-23T14:08:01Z</updated>
		
		<summary type="html">&lt;p&gt;以内容“=== Accomplished this week === * Tested the 4*600+800 model + 150k / 20k / 10k / 5k graph + new 1e-7 with biglm mode. * Get the wer &amp;amp; RT respectively. * Fixed the error...”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;
* Tested the 4*600+800 model + 150k / 20k / 10k / 5k graph + new 1e-7 with biglm mode.&lt;br /&gt;
* Get the wer &amp;amp; RT respectively.&lt;br /&gt;
* Fixed the error of decoder partly.&lt;br /&gt;
* Finished DNN_VAD testing using various DNN.&lt;br /&gt;
&lt;br /&gt;
=== Next Week ===&lt;br /&gt;
* Test the 4*600+800 model + 150k / 20k / 10k / 5k graph + 1e-6.&lt;br /&gt;
* Test the 4*600+800 model + 150k / 20k / 10k / 5k graph + 1e-6.5&lt;br /&gt;
* Find a larger vocab plus a more stringent LM pruning threshold by kind verification.&lt;br /&gt;
* Finish the decoder code about 8-digit recognition.&lt;br /&gt;
* Prepare for the machine learning course.&lt;/div&gt;</summary>
		<author><name>Yinshi</name></author>	</entry>

	</feed>