<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>testing simon &#187; node12</title>
	<atom:link href="http://spirit.blau.in/simon/tag/node12/feed/" rel="self" type="application/rss+xml" />
	<link>http://spirit.blau.in/simon</link>
	<description>my first steps with the simon speech recognition software</description>
	<lastBuildDate>Tue, 10 Jan 2012 14:59:26 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0.1</generator>
		<item>
		<title>How can I export a sam speech model?</title>
		<link>http://spirit.blau.in/simon/2010/02/03/how-can-i-export-a-sam-speech-model/</link>
		<comments>http://spirit.blau.in/simon/2010/02/03/how-can-i-export-a-sam-speech-model/#comments</comments>
		<pubDate>Wed, 03 Feb 2010 14:11:33 +0000</pubDate>
		<dc:creator>producer</dc:creator>
				<category><![CDATA[Ubuntu]]></category>
		<category><![CDATA[node12]]></category>
		<category><![CDATA[sam]]></category>

		<guid isPermaLink="false">http://spirit.blau.in/simon/?p=2446</guid>
		<description><![CDATA[I tried sam again after I had problems a couple of days ago (I used the same paths; I just had to fix the paths to the test files). I used the Build model and the Test model button in conjunction with my German backup files (about 200 German words can be recognized with these [...]]]></description>
			<content:encoded><![CDATA[<p>I tried sam again after <a href="http://spirit.blau.in/simon/2010/01/26/sam-couldnt-open-prompts-file/">I had problems a couple of days ago</a> (I used the same paths; I just had to fix the paths to the test files). I used the <code>Build model</code> and the <code>Test model</code> button in conjunction with my German backup files (about 200 German words can be recognized with these files when everything is configured correctly). It worked.</p>
<p>My question is: how can I import the model that I have built/tested with sam into simon?</p>
<p>simon offers to <code>Manage scenarios</code>: <code>Import</code> and <a href="http://spirit.blau.in/simon/2010/02/03/clear-button-improve-phoneme/#comment-263"><code>Export</code></a> are offered. I tried the <code>Export</code> button. This created an XML file:</p>
<blockquote><p>&lt;!DOCTYPE scenario&gt;<br />
&lt;scenario version=&#8221;1&#8243; icon=&#8221;simon&#8221; name=&#8221;General&#8221; lastModified=&#8221;2010-02-03T14:06:50&#8243;&gt;<br />
&lt;simonCompatibility&gt;<br />
&lt;minimumVersion&gt;<br />
&lt;version&gt;0.2.82&lt;/version&gt;<br />
&lt;/minimumVersion&gt;<br />
&lt;maximumVersion/&gt;<br />
&lt;/simonCompatibility&gt;<br />
&lt;authors&gt;<br />
&lt;author&gt;<br />
&lt;name&gt;Anybody&lt;/name&gt;<br />
&lt;contact&gt;no@mail&lt;/contact&gt;<br />
&lt;/author&gt;<br />
&lt;/authors&gt;<br />
&lt;licence&gt;GPL&lt;/licence&gt;<br />
&lt;vocabulary/&gt;<br />
&lt;grammar&gt;<br />
&lt;structure&gt;Unknown&lt;/structure&gt;<br />
&lt;/grammar&gt;<br />
&lt;actions/&gt;<br />
&lt;trainingtexts/&gt;<br />
&lt;/scenario&gt;</p></blockquote>
<p>I would like to be able to <strong>import my sam speech model into simon</strong>. How can I do this?</p>
<p>What can I import into simon?<br />
- I can press the <code>Import Dictionary</code> button to import an active dictionary and/or a shadow dictionary.<br />
- I can switch to the <code>Grammar</code> tab, press the <code>Import</code> button. I didn&#8217;t try this function yet. I am not too interested because currently I don&#8217;t need a grammar function (200 German words could be recognized without a grammar &#8211; only the terminal <code>Unknown</code> was used; 1000 German words should be possible without grammar, I hope). Of course, if I want to <a href="http://script.blau.in/20091228-kdeshareappssimon-model.tar.gz">restore my German speech model</a> (53 MB), it is necessary to restore the grammar, too. So this <code>Import</code> [Grammar] button might be useful.<br />
- In the <code>Training</code> tab, I can press the <code>Import Trainingsdata</code> button. This should import the <code>prompts</code> file and the corresponding <code>wav</code> files (stored in the <code>training.data</code> folder).</p>
<p>When I take a look at <code>sam</code> &gt; <code>Static model</code>, I can see fields for <code>Base macros</code> and <code>Base stats</code>. Where are these files from my own German 200 words speech model located? When I download the <a href="http://www.repository.voxforge1.org/downloads/Nightly_Builds/AcousticModel-2010-02-03/">English acoustic model from Voxforge</a> (<code>HTK_AcousticModel-2010-02-03_16kHz_16bit_MFCC_O_D.tgz</code>), I can see the following files:</p>
<p><a href="http://spirit.blau.in/simon/files/2010/02/macros-stats.png"><img src="http://spirit.blau.in/simon/files/2010/02/macros-stats-300x247.png" alt="macros-stats" width="300" height="247" class="alignnone size-medium wp-image-2456" /></a></p>
<p>1. <code>macros</code> &#8211; this file is probably usable with <code>sam</code> &gt; <code>Input &amp; output files</code> &gt; <code>Static model</code> &gt; <code>Base macros</code>.<br />
2. <code>stats</code> &#8211; probably usable with <code>sam</code> &gt; <code>Input &amp; output files</code> &gt; <code>Static model</code> &gt; <strong><code>Base stats</code></strong>.</p>
<p>When I build my own German speech model with sam, where are these files &#8211; <code>macros</code> and <code>stats</code> &#8211; located? Where can I find them? I assume that I need them if I want to restore my speech model for the usage with simon, but I am not sure.</p>
<p>This is what I want: Restore my 200 German words speech model (my current problem). Then I want to add more words to this speech model. I am planning to add about 10 words per day on average to my German speech model. It should grow continously. And if something goes wrong, I want to be able to restore from my backup file because I don&#8217;t want to begin again and again from scratch.</p>
<p>The <code>Manage scenarios</code> &gt; <code>Import</code> and <code>Export</code> buttons might be of help in the future.</p>
<p>I already said it earlier, and I say it again because it is important: the user doesn&#8217;t want to loose his own work (= wav recordings that were made with simon). It should be possible to backup (=export) and to restore (=import) all files that are necessary to build a working speech model. </p>
<p>For me, it is OK to specify each specific path like it is possible with sam. But in the end, it has to work with simon.</p>
<p>I want to fine tune my German speech model with sam. Especially, I want to sort out <code>wav</code> files that have a low recognition rate with sam. After I have fine-tuned my German speech model with sam, I want to use it with simon (=import it into simon). How is this possible?</p>
]]></content:encoded>
			<wfw:commentRss>http://spirit.blau.in/simon/2010/02/03/how-can-i-export-a-sam-speech-model/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

