Base Transformation for Environment Adaptation in Continuous Speech Recognition
Identifieur interne : 00CE96 ( Main/Exploration ); précédent : 00CE95; suivant : 00CE97Base Transformation for Environment Adaptation in Continuous Speech Recognition
Auteurs : Y. GongSource :
English descriptors
Abstract
A specific background noise, speaker or transmission line condition of a speech recognizer is referred as an environment. A mismatch between the training and operating environments can severely degrade recognition accuracy. We present a base transformation method for environment adaptation, which converts an environmental difference into a base difference and reduces the difference by a base transformation. Experiments were conducted on adapting to telephone quality speech, to a new speaker and to speech corrupted by additive Gaussian noise. Using two sentences (5 sec duration) as adaptation data, the method gives a telephone line adapted recognition accuracy of 93.5========percnt; and a speaker adapted accuracy of about 90========percnt;, for a city name recognition task. Using nine sentences (20 sec duration) with SNRs better than 10dB, a noise-adapted recognition accuracy of 90========percnt; was obtained on a 206 word recognition task.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001186
- to stream Crin, to step Curation: 001186
- to stream Crin, to step Checkpoint: 003296
- to stream Main, to step Merge: 00D768
- to stream Main, to step Curation: 00CE96
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="746">Base Transformation for Environment Adaptation in Continuous Speech Recognition</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:gong93a</idno>
<date when="1993" year="1993">1993</date>
<idno type="wicri:Area/Crin/Corpus">001186</idno>
<idno type="wicri:Area/Crin/Curation">001186</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001186</idno>
<idno type="wicri:Area/Crin/Checkpoint">003296</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003296</idno>
<idno type="wicri:Area/Main/Merge">00D768</idno>
<idno type="wicri:Area/Main/Curation">00CE96</idno>
<idno type="wicri:Area/Main/Exploration">00CE96</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Base Transformation for Environment Adaptation in Continuous Speech Recognition</title>
<author><name sortKey="Gong, Y" sort="Gong, Y" uniqKey="Gong Y" first="Y." last="Gong">Y. Gong</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>base transformation</term>
<term>environment adaptation</term>
<term>noisy speech recognition</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3587">A specific background noise, speaker or transmission line condition of a speech recognizer is referred as an environment. A mismatch between the training and operating environments can severely degrade recognition accuracy. We present a base transformation method for environment adaptation, which converts an environmental difference into a base difference and reduces the difference by a base transformation. Experiments were conducted on adapting to telephone quality speech, to a new speaker and to speech corrupted by additive Gaussian noise. Using two sentences (5 sec duration) as adaptation data, the method gives a telephone line adapted recognition accuracy of 93.5========percnt; and a speaker adapted accuracy of about 90========percnt;, for a city name recognition task. Using nine sentences (20 sec duration) with SNRs better than 10dB, a noise-adapted recognition accuracy of 90========percnt; was obtained on a 206 word recognition task.</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Gong, Y" sort="Gong, Y" uniqKey="Gong Y" first="Y." last="Gong">Y. Gong</name>
</noCountry>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00CE96 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 00CE96 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Exploration |type= RBID |clé= CRIN:gong93a |texte= Base Transformation for Environment Adaptation in Continuous Speech Recognition }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |