Search of Spoken Documents Retrieves Well Recognized Transcripts
Identifieur interne : 000D99 ( Main/Exploration ); précédent : 000D98; suivant : 000E00Search of Spoken Documents Retrieves Well Recognized Transcripts
Auteurs : Mark Sanderson [Royaume-Uni] ; Mang Shou [Royaume-Uni]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2007.
Abstract
Abstract: This paper presents a series of analyses and experiments on spoken document retrieval systems: search engines that retrieve transcripts produced by speech recognizers. Results show that transcripts that match queries well tend to be recognized more accurately than transcripts that match a query less well. This result was described in past literature, however, no study or explanation of the effect has been provided until now. This paper provides such an analysis showing a relationship between word error rate and query length. The paper expands on past research by increasing the number of recognitions systems that are tested as well as showing the effect in an operational speech retrieval system. Potential future lines of enquiry are also described.
Url:
DOI: 10.1007/978-3-540-71496-5_45
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000D19
- to stream Istex, to step Curation: 000C93
- to stream Istex, to step Checkpoint: 000814
- to stream Main, to step Merge: 000E12
- to stream Main, to step Curation: 000D99
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Search of Spoken Documents Retrieves Well Recognized Transcripts</title><author><name sortKey="Sanderson, Mark" sort="Sanderson, Mark" uniqKey="Sanderson M" first="Mark" last="Sanderson">Mark Sanderson</name></author><author><name sortKey="Shou, Mang" sort="Shou, Mang" uniqKey="Shou M" first="Mang" last="Shou">Mang Shou</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:6E09AA0DC520A24179678A924053234288CBAB2D</idno><date when="2007" year="2007">2007</date><idno type="doi">10.1007/978-3-540-71496-5_45</idno><idno type="url">https://api.istex.fr/document/6E09AA0DC520A24179678A924053234288CBAB2D/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000D19</idno><idno type="wicri:Area/Istex/Curation">000C93</idno><idno type="wicri:Area/Istex/Checkpoint">000814</idno><idno type="wicri:doubleKey">0302-9743:2007:Sanderson M:search:of:spoken</idno><idno type="wicri:Area/Main/Merge">000E12</idno><idno type="wicri:Area/Main/Curation">000D99</idno><idno type="wicri:Area/Main/Exploration">000D99</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Search of Spoken Documents Retrieves Well Recognized Transcripts</title><author><name sortKey="Sanderson, Mark" sort="Sanderson, Mark" uniqKey="Sanderson M" first="Mark" last="Sanderson">Mark Sanderson</name><affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country><wicri:regionArea>Department of Information Studies, University of Sheffield, Western Bank, Sheffield, S10 2TN</wicri:regionArea><wicri:noRegion>S10 2TN</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Royaume-Uni</country></affiliation></author><author><name sortKey="Shou, Mang" sort="Shou, Mang" uniqKey="Shou M" first="Mang" last="Shou">Mang Shou</name><affiliation wicri:level="1"><country xml:lang="fr">Royaume-Uni</country><wicri:regionArea>Department of Information Studies, University of Sheffield, Western Bank, Sheffield, S10 2TN</wicri:regionArea><wicri:noRegion>S10 2TN</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Royaume-Uni</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2007</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">6E09AA0DC520A24179678A924053234288CBAB2D</idno><idno type="DOI">10.1007/978-3-540-71496-5_45</idno><idno type="ChapterID">45</idno><idno type="ChapterID">Chap45</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: This paper presents a series of analyses and experiments on spoken document retrieval systems: search engines that retrieve transcripts produced by speech recognizers. Results show that transcripts that match queries well tend to be recognized more accurately than transcripts that match a query less well. This result was described in past literature, however, no study or explanation of the effect has been provided until now. This paper provides such an analysis showing a relationship between word error rate and query length. The paper expands on past research by increasing the number of recognitions systems that are tested as well as showing the effect in an operational speech retrieval system. Potential future lines of enquiry are also described.</div></front></TEI><affiliations><list><country><li>Royaume-Uni</li></country></list><tree><country name="Royaume-Uni"><noRegion><name sortKey="Sanderson, Mark" sort="Sanderson, Mark" uniqKey="Sanderson M" first="Mark" last="Sanderson">Mark Sanderson</name></noRegion><name sortKey="Sanderson, Mark" sort="Sanderson, Mark" uniqKey="Sanderson M" first="Mark" last="Sanderson">Mark Sanderson</name><name sortKey="Shou, Mang" sort="Shou, Mang" uniqKey="Shou M" first="Mang" last="Shou">Mang Shou</name><name sortKey="Shou, Mang" sort="Shou, Mang" uniqKey="Shou M" first="Mang" last="Shou">Mang Shou</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 000D99 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000D99 | 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:6E09AA0DC520A24179678A924053234288CBAB2D
|texte= Search of Spoken Documents Retrieves Well Recognized Transcripts
}}
| This area was generated with Dilib version V0.6.32. |  |