Rejecto – LanguageModel – Politepix /forums/topic/rejecto-languagemodel/feed/ Tue, 23 Apr 2024 14:44:48 +0000 https://bbpress.org/?v=2.6.9 en-US /forums/topic/rejecto-languagemodel/#post-14823 <![CDATA[Rejecto – LanguageModel]]> /forums/topic/rejecto-languagemodel/#post-14823 Fri, 07 Dec 2012 12:50:34 +0000 lookbadgers It’s been a while since I last played with OpenEars, it’s great to see the enhancements and addition of sound recording testing. I hope you are doing well, just a quick question.

Can a language model be used with Rejecto? Or are there any plans to add support for this?

Currently it uses generateRejectingLanguageModelFromArray but for future performance improvements would a language model be faster?

Thank you,

]]>
/forums/topic/rejecto-languagemodel/#post-14824 <![CDATA[Reply To: Rejecto – LanguageModel]]> /forums/topic/rejecto-languagemodel/#post-14824 Fri, 07 Dec 2012 13:00:04 +0000 Halle Winkler Hiya and welcome back,

I can take this under advisement as a requested feature, but the main thing Rejecto does is create a language model that incorporates the rejection features and has the rejecting elements added to the language model’s probability calculation, so there is no getting around the requirement to recalculate the lm’s probability model even if you start with a completed one. It also has to check and make sure that you aren’t already using one of the rejection phonemes in your real model and if so remove that phoneme from the rejection model, meaning that a premade .dic would also still need processing.

Not saying there is no way, just that it isn’t trivial and it won’t vastly cut down on processing time.

If you are seeing unpleasantly slow generation for a dynamic model, maybe you want to look at this tip I wrote up which had a suggestion at the end for avoiding any repeated use of the fallback pronunciation generation technique (i.e. the slow one):

/2012/12/04/openears-tips-and-tricks-5-customizing-the-master-phonetic-dictionary-or-using-a-new-one/

]]>
This XML file does not appear to have any style information associated with it. The document tree is shown below.
<rss 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" version="2.0">
<channel>
<title>Rejecto – LanguageModel – Politepix</title>
<atom:link href="/forums/topic/rejecto-languagemodel/feed/" rel="self" type="application/rss+xml"/>
<link>/forums/topic/rejecto-languagemodel/feed/</link>
<description/>
<lastBuildDate>Tue, 23 Apr 2024 14:44:48 +0000</lastBuildDate>
<generator>https://bbpress.org/?v=2.6.9</generator>
<language>en-US</language>
<item>
<guid>/forums/topic/rejecto-languagemodel/#post-14823</guid>
<title>
<![CDATA[ Rejecto &#8211; LanguageModel ]]>
</title>
<link>/forums/topic/rejecto-languagemodel/#post-14823</link>
<pubDate>Fri, 07 Dec 2012 12:50:34 +0000</pubDate>
<dc:creator>lookbadgers</dc:creator>
<description>
<![CDATA[ <p>It&#8217;s been a while since I last played with OpenEars, it&#8217;s great to see the enhancements and addition of sound recording testing. I hope you are doing well, just a quick question.</p> <p>Can a language model be used with Rejecto? Or are there any plans to add support for this?</p> <p>Currently it uses generateRejectingLanguageModelFromArray but for future performance improvements would a language model be faster?</p> <p>Thank you,</p> ]]>
</description>
</item>
<item>
<guid>/forums/topic/rejecto-languagemodel/#post-14824</guid>
<title>
<![CDATA[ Reply To: Rejecto – LanguageModel ]]>
</title>
<link>/forums/topic/rejecto-languagemodel/#post-14824</link>
<pubDate>Fri, 07 Dec 2012 13:00:04 +0000</pubDate>
<dc:creator>Halle Winkler</dc:creator>
<description>
<![CDATA[ <p>Hiya and welcome back,</p> <p>I can take this under advisement as a requested feature, but the main thing Rejecto does is create a language model that incorporates the rejection features and has the rejecting elements added to the language model&#8217;s probability calculation, so there is no getting around the requirement to recalculate the lm&#8217;s probability model even if you start with a completed one. It also has to check and make sure that you aren&#8217;t already using one of the rejection phonemes in your real model and if so remove that phoneme from the rejection model, meaning that a premade .dic would also still need processing.</p> <p>Not saying there is no way, just that it isn&#8217;t trivial and it won&#8217;t vastly cut down on processing time.</p> <p>If you are seeing unpleasantly slow generation for a dynamic model, maybe you want to look at this tip I wrote up which had a suggestion at the end for avoiding any repeated use of the fallback pronunciation generation technique (i.e. the slow one):</p> <p><a href="/2012/12/04/openears-tips-and-tricks-5-customizing-the-master-phonetic-dictionary-or-using-a-new-one/">/2012/12/04/openears-tips-and-tricks-5-customizing-the-master-phonetic-dictionary-or-using-a-new-one/</a></p> ]]>
</description>
</item>
</channel>
</rss>