Audio Lifelog Search System Using a Topic Model for Reducing Recognition Errors
Identifieur interne : 000504 ( Main/Exploration ); précédent : 000503; suivant : 000505Audio Lifelog Search System Using a Topic Model for Reducing Recognition Errors
Auteurs : Taro Tezuka [Japon] ; Akira Maeda [Japon]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2011.
Abstract
Abstract: A system that records daily conversations is one of the most useful types of lifelogs. It is, however, not widely used due to the low precision of speech recognizers when applied to conversations. To solve this problem, we propose a method that uses a topic model to reduce incorrectly recognized words. Specifically, we measure relevancy between a term and the other words in the conversation and remove those that come below the threshold. An audio lifelog search system was implemented using the method. Experiments showed that our method is effective in compensating recognition errors of speech recognizers. We observed increase in both precision and recall. The results indicate that our method has an ability to reduce errors in the index of a lifelog search system.
Url:
DOI: 10.1007/978-3-642-20152-3_6
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000700
- to stream Istex, to step Curation: 000692
- to stream Istex, to step Checkpoint: 000161
- to stream Main, to step Merge: 000510
- to stream Main, to step Curation: 000504
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Audio Lifelog Search System Using a Topic Model for Reducing Recognition Errors</title><author><name sortKey="Tezuka, Taro" sort="Tezuka, Taro" uniqKey="Tezuka T" first="Taro" last="Tezuka">Taro Tezuka</name></author><author><name sortKey="Maeda, Akira" sort="Maeda, Akira" uniqKey="Maeda A" first="Akira" last="Maeda">Akira Maeda</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:34E511299B2BAAA0F1F35941F2E49E2A5CAF63C7</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1007/978-3-642-20152-3_6</idno><idno type="url">https://api.istex.fr/document/34E511299B2BAAA0F1F35941F2E49E2A5CAF63C7/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000700</idno><idno type="wicri:Area/Istex/Curation">000692</idno><idno type="wicri:Area/Istex/Checkpoint">000161</idno><idno type="wicri:doubleKey">0302-9743:2011:Tezuka T:audio:lifelog:search</idno><idno type="wicri:Area/Main/Merge">000510</idno><idno type="wicri:Area/Main/Curation">000504</idno><idno type="wicri:Area/Main/Exploration">000504</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Audio Lifelog Search System Using a Topic Model for Reducing Recognition Errors</title><author><name sortKey="Tezuka, Taro" sort="Tezuka, Taro" uniqKey="Tezuka T" first="Taro" last="Tezuka">Taro Tezuka</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>College of Information Science and Engineering, Ritsumeikan University</wicri:regionArea><wicri:noRegion>Ritsumeikan University</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Japon</country></affiliation></author><author><name sortKey="Maeda, Akira" sort="Maeda, Akira" uniqKey="Maeda A" first="Akira" last="Maeda">Akira Maeda</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>College of Information Science and Engineering, Ritsumeikan University</wicri:regionArea><wicri:noRegion>Ritsumeikan University</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Japon</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2011</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">34E511299B2BAAA0F1F35941F2E49E2A5CAF63C7</idno><idno type="DOI">10.1007/978-3-642-20152-3_6</idno><idno type="ChapterID">6</idno><idno type="ChapterID">Chap6</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: A system that records daily conversations is one of the most useful types of lifelogs. It is, however, not widely used due to the low precision of speech recognizers when applied to conversations. To solve this problem, we propose a method that uses a topic model to reduce incorrectly recognized words. Specifically, we measure relevancy between a term and the other words in the conversation and remove those that come below the threshold. An audio lifelog search system was implemented using the method. Experiments showed that our method is effective in compensating recognition errors of speech recognizers. We observed increase in both precision and recall. The results indicate that our method has an ability to reduce errors in the index of a lifelog search system.</div></front></TEI><affiliations><list><country><li>Japon</li></country></list><tree><country name="Japon"><noRegion><name sortKey="Tezuka, Taro" sort="Tezuka, Taro" uniqKey="Tezuka T" first="Taro" last="Tezuka">Taro Tezuka</name></noRegion><name sortKey="Maeda, Akira" sort="Maeda, Akira" uniqKey="Maeda A" first="Akira" last="Maeda">Akira Maeda</name><name sortKey="Maeda, Akira" sort="Maeda, Akira" uniqKey="Maeda A" first="Akira" last="Maeda">Akira Maeda</name><name sortKey="Tezuka, Taro" sort="Tezuka, Taro" uniqKey="Tezuka T" first="Taro" last="Tezuka">Taro Tezuka</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000504 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000504 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:34E511299B2BAAA0F1F35941F2E49E2A5CAF63C7
|texte= Audio Lifelog Search System Using a Topic Model for Reducing Recognition Errors
}}
| This area was generated with Dilib version V0.6.32. |  |