Duration of Phones as Function of Utterance Length and its Use in Automatic Speech
Identifieur interne : 00D817 ( Main/Merge ); précédent : 00D816; suivant : 00D818Duration of Phones as Function of Utterance Length and its Use in Automatic Speech
Auteurs : Y. Gong ; W. C. TreurnietSource :
English descriptors
Abstract
Duration probability of phonemes is widely used as a constraint in phoneme-based continuous speech recognizers, and is known to improve recognition accuracy. Usually, models of phoneme duration are extracted from continuous utterances of sentences in a training database. However, tokens obtained from shorter utterances may not be well represented by models created from longer utterances. We designed an experiment to compute observed average phoneme duration as a function of the number of phonemes per utterance. We observed that the average duration consistently increases as the number of phonemes per utterance increases. The experiment showed that the average duration of phonemes in words spoken in isolation may be as much as 50========percnt; longer than the average duration of phonemes in continuously spoken sentences. The variation of phoneme duration as a function of utterance duration was modeled in both the phoneme probability estimation stage and the utterance search stage of a recognition system. As a result, a 47========percnt; reduction in word recognition errors was obtained.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001187
- to stream Crin, to step Curation: 001187
- to stream Crin, to step Checkpoint: 003345
Links to Exploration step
CRIN:gong93bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="464">Duration of Phones as Function of Utterance Length and its Use in Automatic Speech</title></titleStmt><publicationStmt><idno type="RBID">CRIN:gong93b</idno><date when="1993" year="1993">1993</date><idno type="wicri:Area/Crin/Corpus">001187</idno><idno type="wicri:Area/Crin/Curation">001187</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001187</idno><idno type="wicri:Area/Crin/Checkpoint">003345</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003345</idno><idno type="wicri:Area/Main/Merge">00D817</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Duration of Phones as Function of Utterance Length and its Use in Automatic Speech</title><author><name sortKey="Gong, Y" sort="Gong, Y" uniqKey="Gong Y" first="Y." last="Gong">Y. Gong</name></author><author><name sortKey="Treurniet, W C" sort="Treurniet, W C" uniqKey="Treurniet W" first="W. C." last="Treurniet">W. C. Treurniet</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>duration probability</term><term>phoneme duration</term><term>phoneme-based speech recognition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="3491">Duration probability of phonemes is widely used as a constraint in phoneme-based continuous speech recognizers, and is known to improve recognition accuracy. Usually, models of phoneme duration are extracted from continuous utterances of sentences in a training database. However, tokens obtained from shorter utterances may not be well represented by models created from longer utterances. We designed an experiment to compute observed average phoneme duration as a function of the number of phonemes per utterance. We observed that the average duration consistently increases as the number of phonemes per utterance increases. The experiment showed that the average duration of phonemes in words spoken in isolation may be as much as 50========percnt; longer than the average duration of phonemes in continuously spoken sentences. The variation of phoneme duration as a function of utterance duration was modeled in both the phoneme probability estimation stage and the utterance search stage of a recognition system. As a result, a 47========percnt; reduction in word recognition errors was obtained.</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 00D817 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00D817 | 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:gong93b
|texte= Duration of Phones as Function of Utterance Length and its Use in Automatic Speech
}}
| This area was generated with Dilib version V0.6.33. |  |