Noise Independent Speech Recognition for a Variety of Noise Types
Identifieur interne : 00D406 ( Main/Merge ); précédent : 00D405; suivant : 00D407Noise Independent Speech Recognition for a Variety of Noise Types
Auteurs : W.-C. Treurniet ; Y. GongSource :
English descriptors
- KwdEn :
Abstract
By a base transformation technique, we previously reported a recognizer which gives a noise-adapted recognition rate of 90========percnt; under 10 dB SNR on a vocabulary of 206 words. This rate is 97========percnt; of the recognition rate for clean speech. The technique is extended here so that the input noise is first recognized as one of a set reference noises, and the noise reference is used for the base transformation of the noisy utterance. Using 32 reference noise classes, for speech signals corrupted by noises of unknown natures (either Gaussian, bus or aircrafts) with SNR randomly from 10 to 40 dB), we obtained a noise-independent recognition rate of about 95.5========percnt; of the recognition rate for clean speech.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001599
- to stream Crin, to step Curation: 001599
- to stream Crin, to step Checkpoint: 003108
Links to Exploration step
CRIN:treurniet94aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="228">Noise Independent Speech Recognition for a Variety of Noise Types</title></titleStmt><publicationStmt><idno type="RBID">CRIN:treurniet94a</idno><date when="1994" year="1994">1994</date><idno type="wicri:Area/Crin/Corpus">001599</idno><idno type="wicri:Area/Crin/Curation">001599</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001599</idno><idno type="wicri:Area/Crin/Checkpoint">003108</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003108</idno><idno type="wicri:Area/Main/Merge">00D406</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Noise Independent Speech Recognition for a Variety of Noise Types</title><author><name sortKey="Treurniet, W C" sort="Treurniet, W C" uniqKey="Treurniet W" first="W.-C." last="Treurniet">W.-C. Treurniet</name></author><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>speech recognition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="1743">By a base transformation technique, we previously reported a recognizer which gives a noise-adapted recognition rate of 90========percnt; under 10 dB SNR on a vocabulary of 206 words. This rate is 97========percnt; of the recognition rate for clean speech. The technique is extended here so that the input noise is first recognized as one of a set reference noises, and the noise reference is used for the base transformation of the noisy utterance. Using 32 reference noise classes, for speech signals corrupted by noises of unknown natures (either Gaussian, bus or aircrafts) with SNR randomly from 10 to 40 dB), we obtained a noise-independent recognition rate of about 95.5========percnt; of the recognition rate for clean speech.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00D406 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00D406 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Merge
|type= RBID
|clé= CRIN:treurniet94a
|texte= Noise Independent Speech Recognition for a Variety of Noise Types
}}
| This area was generated with Dilib version V0.6.33. |  |