Lexical Access for Speech Understanding using Minimum Message Length Encoding

Lexical Access for Speech Understanding using Minimum Message Length Encoding

The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criteri...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Thomas, Ian, Zukerman, Ingrid, Oliver, Jonathan, Albrecht, David, Raskutti, Bhavani
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computation and Language
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Thomas, Ian
Zukerman, Ingrid
Oliver, Jonathan
Albrecht, David
Raskutti, Bhavani
description The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criterion for solving the Lexical Access Problem. We model sentences using phoneme realizations seen in training, and word and part-of-speech information obtained from text corpora. We show results on multiple-speaker, continuous, read speech and discuss a heuristic using equivalence classes of similar sounding words which speeds up the recognition process without significant deterioration in recognition accuracy.
doi_str_mv 10.48550/arxiv.1302.1572
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1302_1572</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1302_1572</sourcerecordid><originalsourceid>FETCH-LOGICAL-a652-bbc443478fb90b3b01006bb35c639cf495e39758a7971ddd47b05e9f550297233</originalsourceid><addsrcrecordid>eNotz7tqwzAYBWAtGUrSvVPRC9jV1bLGENIL2HRoOhtdfjmCWAlSUtK3b9x2OWc5HPgQeqCkFq2U5Mnka_yqKSesplKxO9R3cI3OHPDaOSgFh2PGHycAt8efyUMuZ5N8TCO-lDn7mOJ0mXB_25oRcAdpPO_xNrnjvFqhRTCHAvf_vUS75-1u81p17y9vm3VXmUayylonBBeqDVYTyy2hhDTWcukarl0QWgLXSrZGaUW990JZIkGHG4BpxThfose_21_OcMpxMvl7mFnDzOI_gABHIA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Lexical Access for Speech Understanding using Minimum Message Length Encoding</title><source>arXiv.org</source><creator>Thomas, Ian ; Zukerman, Ingrid ; Oliver, Jonathan ; Albrecht, David ; Raskutti, Bhavani</creator><creatorcontrib>Thomas, Ian ; Zukerman, Ingrid ; Oliver, Jonathan ; Albrecht, David ; Raskutti, Bhavani</creatorcontrib><description>The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criterion for solving the Lexical Access Problem. We model sentences using phoneme realizations seen in training, and word and part-of-speech information obtained from text corpora. We show results on multiple-speaker, continuous, read speech and discuss a heuristic using equivalence classes of similar sounding words which speeds up the recognition process without significant deterioration in recognition accuracy.</description><identifier>DOI: 10.48550/arxiv.1302.1572</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2013-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1302.1572$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1302.1572$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Thomas, Ian</creatorcontrib><creatorcontrib>Zukerman, Ingrid</creatorcontrib><creatorcontrib>Oliver, Jonathan</creatorcontrib><creatorcontrib>Albrecht, David</creatorcontrib><creatorcontrib>Raskutti, Bhavani</creatorcontrib><title>Lexical Access for Speech Understanding using Minimum Message Length Encoding</title><description>The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criterion for solving the Lexical Access Problem. We model sentences using phoneme realizations seen in training, and word and part-of-speech information obtained from text corpora. We show results on multiple-speaker, continuous, read speech and discuss a heuristic using equivalence classes of similar sounding words which speeds up the recognition process without significant deterioration in recognition accuracy.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7tqwzAYBWAtGUrSvVPRC9jV1bLGENIL2HRoOhtdfjmCWAlSUtK3b9x2OWc5HPgQeqCkFq2U5Mnka_yqKSesplKxO9R3cI3OHPDaOSgFh2PGHycAt8efyUMuZ5N8TCO-lDn7mOJ0mXB_25oRcAdpPO_xNrnjvFqhRTCHAvf_vUS75-1u81p17y9vm3VXmUayylonBBeqDVYTyy2hhDTWcukarl0QWgLXSrZGaUW990JZIkGHG4BpxThfose_21_OcMpxMvl7mFnDzOI_gABHIA</recordid><startdate>20130206</startdate><enddate>20130206</enddate><creator>Thomas, Ian</creator><creator>Zukerman, Ingrid</creator><creator>Oliver, Jonathan</creator><creator>Albrecht, David</creator><creator>Raskutti, Bhavani</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20130206</creationdate><title>Lexical Access for Speech Understanding using Minimum Message Length Encoding</title><author>Thomas, Ian ; Zukerman, Ingrid ; Oliver, Jonathan ; Albrecht, David ; Raskutti, Bhavani</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a652-bbc443478fb90b3b01006bb35c639cf495e39758a7971ddd47b05e9f550297233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Thomas, Ian</creatorcontrib><creatorcontrib>Zukerman, Ingrid</creatorcontrib><creatorcontrib>Oliver, Jonathan</creatorcontrib><creatorcontrib>Albrecht, David</creatorcontrib><creatorcontrib>Raskutti, Bhavani</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Thomas, Ian</au><au>Zukerman, Ingrid</au><au>Oliver, Jonathan</au><au>Albrecht, David</au><au>Raskutti, Bhavani</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Lexical Access for Speech Understanding using Minimum Message Length Encoding</atitle><date>2013-02-06</date><risdate>2013</risdate><abstract>The Lexical Access Problem consists of determining the intended sequence of words corresponding to an input sequence of phonemes (basic speech sounds) that come from a low-level phoneme recognizer. In this paper we present an information-theoretic approach based on the Minimum Message Length Criterion for solving the Lexical Access Problem. We model sentences using phoneme realizations seen in training, and word and part-of-speech information obtained from text corpora. We show results on multiple-speaker, continuous, read speech and discuss a heuristic using equivalence classes of similar sounding words which speeds up the recognition process without significant deterioration in recognition accuracy.</abstract><doi>10.48550/arxiv.1302.1572</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1302.1572
ispartof
issn
language eng
recordid cdi_arxiv_primary_1302_1572
source arXiv.org
subjects Computer Science - Computation and Language
title Lexical Access for Speech Understanding using Minimum Message Length Encoding
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A46%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Lexical%20Access%20for%20Speech%20Understanding%20using%20Minimum%20Message%20Length%20Encoding&rft.au=Thomas,%20Ian&rft.date=2013-02-06&rft_id=info:doi/10.48550/arxiv.1302.1572&rft_dat=%3Carxiv_GOX%3E1302_1572%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true