<title>Any recommendation on Hypothesis scoring limits? – Politepix</title>
<atom:link href="/forums/topic/any-recommendation-on-hypothesis-scoring-limits/feed/" rel="self" type="application/rss+xml"/>
<link>/forums/topic/any-recommendation-on-hypothesis-scoring-limits/feed/</link>
<description/>
<lastBuildDate>Tue, 23 Apr 2024 14:48:16 +0000</lastBuildDate>
<generator>https://bbpress.org/?v=2.6.9</generator>
<language>en-US</language>
<item>
<guid>/forums/topic/any-recommendation-on-hypothesis-scoring-limits/#post-1015440</guid>
<title>
<![CDATA[ Any recommendation on Hypothesis scoring limits? ]]>
...</title>
<link>/forums/topic/any-recommendation-on-hypothesis-scoring-limits/#post-1015440</link>
<pubDate>Tue, 22 Jan 2013 13:52:57 +0000</pubDate>
<dc:creator>Geri</dc:creator>
<description>
<![CDATA[
<p>Is there any recommendation on hypothesis scoring limits?<br />
I’d need around 4 categories, I’m just prototypeing now.</p>
<p>You said “WORD”.<br />
Seems you said “WORD”.<br />
Probably you said something like “WORD”.<br />
Sorry, I couldn’t understand what you said.</p>
<p>What could be the hypothesis scrore limits for these?</p>
]]>
...</description>
...</item>
<item>
<guid>/forums/topic/any-recommendation-on-hypothesis-scoring-limits/#post-1015441</guid>
<title>
<![CDATA[ Reply To: Any recommendation on Hypothesis scoring limits? ]]>
...</title>
<link>/forums/topic/any-recommendation-on-hypothesis-scoring-limits/#post-1015441</link>
<pubDate>Tue, 22 Jan 2013 14:08:29 +0000</pubDate>
<dc:creator>Halle Winkler</dc:creator>
<description>
<![CDATA[
<p>Hello,</p>
<p>Here are the previous discussions:</p>
<p><a href="/forums/topic/how-does-recognition-score-works/">/forums/topic/how-does-recognition-score-works/</a><br />
<a href="/forums/topic/scores-used-in-openears/">/forums/topic/scores-used-in-openears/</a></p>
<p>You can’t use ranges to limit because you don’t know what the environmental factors are, but something you can experiment with is detecting cases where the top n-best and the second-closest n-best are close and the overall range is large. i.e. 1-best is -50000 and 2-best is -50500 suggests to me that it’s a close call. But you can’t say “below -50000 is wrong”.</p>
]]>
...</description>
...</item>