<?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=140708_-_Fanhu_Bie</id>
		<title>140708 - Fanhu Bie - 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=140708_-_Fanhu_Bie"/>
		<link rel="alternate" type="text/html" href="http://index.cslt.org/mediawiki/index.php?title=140708_-_Fanhu_Bie&amp;action=history"/>
		<updated>2026-04-14T13:57:58Z</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=140708_-_Fanhu_Bie&amp;diff=10406&amp;oldid=prev</id>
		<title>Biefh：以内容“Last Week:  1. Modify the ivector to use the DNN result as the weight to plus to the F0 statistics.  2. Take out the 1`s experiment, go on to modify the Loading matrix ...”创建新页面</title>
		<link rel="alternate" type="text/html" href="http://index.cslt.org/mediawiki/index.php?title=140708_-_Fanhu_Bie&amp;diff=10406&amp;oldid=prev"/>
				<updated>2014-07-08T00:58:54Z</updated>
		
		<summary type="html">&lt;p&gt;以内容“Last Week:  1. Modify the ivector to use the DNN result as the weight to plus to the F0 statistics.  2. Take out the 1`s experiment, go on to modify the Loading matrix ...”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;Last Week:&lt;br /&gt;
&lt;br /&gt;
1. Modify the ivector to use the DNN result as the weight to plus to the F0 statistics.&lt;br /&gt;
&lt;br /&gt;
2. Take out the 1`s experiment, go on to modify the Loading matrix training code.&lt;br /&gt;
&lt;br /&gt;
3. Code for the supervised UBM training, which will be used in the DNN-based ivector training code.&lt;br /&gt;
&lt;br /&gt;
This Week:&lt;br /&gt;
&lt;br /&gt;
1. ChinaSIP2014&lt;br /&gt;
&lt;br /&gt;
2. Modify the re-weighted T matrix training code and take out the experiment.&lt;br /&gt;
&lt;br /&gt;
3. Train the supervised UBM and modify the code to make a unit.&lt;/div&gt;</summary>
		<author><name>Biefh</name></author>	</entry>

	</feed>