<?xml version="1.0" encoding="UTF-8"?>

<modsCollection xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd">
<mods version="3.3">

<genre>conference paper</genre>

<titleInfo><title>On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition</title></titleInfo>





<name type="personal">
  <namePart type="given">Volker</namePart>
  <namePart type="family">Leutnant</namePart>
  <role><roleTerm type="text">author</roleTerm> </role></name>
<name type="personal">
  <namePart type="given">Reinhold</namePart>
  <namePart type="family">Haeb-Umbach</namePart>
  <role><roleTerm type="text">author</roleTerm> </role><identifier type="local">242</identifier></name>







<name type="corporate">
  <namePart></namePart>
  <identifier type="local">54</identifier>
  <role>
    <roleTerm type="text">department</roleTerm>
  </role>
</name>








<abstract lang="eng">In this paper we present an Uncertainty Decoding rule which exploits feature reliability information and interframe correlation for noise robust speech recognition. The reliability information can be obtained either from conditional Bayesian estimation, where speech and noise feature vectors are tracked jointly, or by augmenting conventional point estimation methods with heuristics about the estimator&apos;s reliability. Experimental results on the AURORA2 database demonstrate on the one hand that Uncertainty Decoding improves recognition performance, while on the other hand it is seen that the severe approximations needed to arrive at computationally tractable solutions have their noticable impact on recognition performance.</abstract>

<originInfo><dateIssued encoding="w3cdtf">2009</dateIssued>
</originInfo>
<language><languageTerm authority="iso639-2b" type="code">eng</languageTerm>
</language>



<relatedItem type="host"><titleInfo><title>International Conference on Acoustics (NAG/DAGA 2009)</title></titleInfo>
<part>
</part>
</relatedItem>


<extension>
<bibliographicCitation>
<apa>Leutnant, V., &amp;#38; Haeb-Umbach, R. (2009). On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition. In &lt;i&gt;International Conference on Acoustics (NAG/DAGA 2009)&lt;/i&gt;.</apa>
<ieee>V. Leutnant and R. Haeb-Umbach, “On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition,” in &lt;i&gt;International Conference on Acoustics (NAG/DAGA 2009)&lt;/i&gt;, 2009.</ieee>
<short>V. Leutnant, R. Haeb-Umbach, in: International Conference on Acoustics (NAG/DAGA 2009), 2009.</short>
<chicago>Leutnant, Volker, and Reinhold Haeb-Umbach. “On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition.” In &lt;i&gt;International Conference on Acoustics (NAG/DAGA 2009)&lt;/i&gt;, 2009.</chicago>
<mla>Leutnant, Volker, and Reinhold Haeb-Umbach. “On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition.” &lt;i&gt;International Conference on Acoustics (NAG/DAGA 2009)&lt;/i&gt;, 2009.</mla>
<ama>Leutnant V, Haeb-Umbach R. On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition. In: &lt;i&gt;International Conference on Acoustics (NAG/DAGA 2009)&lt;/i&gt;. ; 2009.</ama>
<bibtex>@inproceedings{Leutnant_Haeb-Umbach_2009, title={On the Estimation and Use of Feature Reliability Information for Noise Robust Speech Recognition}, booktitle={International Conference on Acoustics (NAG/DAGA 2009)}, author={Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2009} }</bibtex>
</bibliographicCitation>
</extension>
<recordInfo><recordIdentifier>11859</recordIdentifier><recordCreationDate encoding="w3cdtf">2019-07-12T05:29:38Z</recordCreationDate><recordChangeDate encoding="w3cdtf">2022-01-06T06:51:11Z</recordChangeDate>
</recordInfo>
</mods>
</modsCollection>
