Base Transformation for Environment Adaptation in Continuous Speech Recognition
Identifieur interne : 001186 ( Crin/Corpus ); précédent : 001185; suivant : 001187Base 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.
Links to Exploration step
CRIN:gong93aLe 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></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><BibTex type="inproceedings"><ref>gong93a</ref><crinnumber>93-R-171</crinnumber><category>3</category><equipe>RFIA</equipe><author><e>Gong, Y.</e></author><title>Base Transformation for Environment Adaptation in Continuous Speech Recognition</title><booktitle>{Proceedings 3rd European Conference onSpeech Communication and Technology, Berlin (Germany)}</booktitle><year>1993</year><volume>3</volume><pages>2227-2230</pages><month>sep</month><keywords><e>environment adaptation</e><e>base transformation</e><e>noisy speech recognition</e></keywords><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.</abstract></BibTex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001186 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Corpus/biblio.hfd -nk 001186 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Crin
|étape= Corpus
|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. |  |