Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants

Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants

Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g., /r/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic /r/ in the PERCEPT-R Corpus. Gated recurrent neural netwo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-05
Hauptverfasser: Benway, Nina R, Preston, Jonathan L, Salekin, Asif, Xiao, Yi, Sharma, Harshit, McAllister, Tara
Format: Artikel
Sprache:eng
Schlagworte:
Age
Recurrent neural networks
Sex
Speech sounds
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Benway, Nina R
Preston, Jonathan L
Salekin, Asif
Xiao, Yi
Sharma, Harshit
McAllister, Tara
description Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g., /r/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic /r/ in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score =.81 ({\sigma}x=.10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.
doi_str_mv 10.48550/arxiv.2305.16111
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2305_16111</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2819557378</sourcerecordid><originalsourceid>FETCH-LOGICAL-a951-cebe05f31d3b5f65294a703ae72d702f193626e74ab4de837e89f24e4fd357f33</originalsourceid><addsrcrecordid>eNotkE1PAjEYhBsTEwnyAzzZxPNC27fd7h4JipgQTYSbh02hb6EEttjuGvDXy4enmcOTycwQ8sBZXxZKsYGJB__TF8BUn-ec8xvSEQA8K6QQd6SX0oYxJnItlIIO-RptTUreHX29op_r0Pilb440ODqIA-prOtsjLtd0Ftra0mefQrQYaZvO_HCFmaltNsMDfQ9xZ7b-Fy0dn23dpHty68w2Ye9fu2Q-fpmPJtn04_VtNJxmplQ8W-ICmXLALSyUy5UopdEMDGphNROOl5CLHLU0C2mxAI1F6YRE6Swo7QC65PEae1le7aPfmXiszg9UlwdOxNOV2Mfw3WJqqk1oY33qVImCl0pp0AX8AUZHXc4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2819557378</pqid></control><display><type>article</type><title>Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Benway, Nina R ; Preston, Jonathan L ; Salekin, Asif ; Xiao, Yi ; Sharma, Harshit ; McAllister, Tara</creator><creatorcontrib>Benway, Nina R ; Preston, Jonathan L ; Salekin, Asif ; Xiao, Yi ; Sharma, Harshit ; McAllister, Tara</creatorcontrib><description>Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g., /r/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic /r/ in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score =.81 ({\sigma}x=.10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2305.16111</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Age ; Recurrent neural networks ; Sex ; Speech sounds</subject><ispartof>arXiv.org, 2023-05</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.21437/Interspeech.2023-312$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2305.16111$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Benway, Nina R</creatorcontrib><creatorcontrib>Preston, Jonathan L</creatorcontrib><creatorcontrib>Salekin, Asif</creatorcontrib><creatorcontrib>Xiao, Yi</creatorcontrib><creatorcontrib>Sharma, Harshit</creatorcontrib><creatorcontrib>McAllister, Tara</creatorcontrib><title>Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants</title><title>arXiv.org</title><description>Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g., /r/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic /r/ in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score =.81 ({\sigma}x=.10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.</description><subject>Age</subject><subject>Recurrent neural networks</subject><subject>Sex</subject><subject>Speech sounds</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotkE1PAjEYhBsTEwnyAzzZxPNC27fd7h4JipgQTYSbh02hb6EEttjuGvDXy4enmcOTycwQ8sBZXxZKsYGJB__TF8BUn-ec8xvSEQA8K6QQd6SX0oYxJnItlIIO-RptTUreHX29op_r0Pilb440ODqIA-prOtsjLtd0Ftra0mefQrQYaZvO_HCFmaltNsMDfQ9xZ7b-Fy0dn23dpHty68w2Ye9fu2Q-fpmPJtn04_VtNJxmplQ8W-ICmXLALSyUy5UopdEMDGphNROOl5CLHLU0C2mxAI1F6YRE6Swo7QC65PEae1le7aPfmXiszg9UlwdOxNOV2Mfw3WJqqk1oY33qVImCl0pp0AX8AUZHXc4</recordid><startdate>20230525</startdate><enddate>20230525</enddate><creator>Benway, Nina R</creator><creator>Preston, Jonathan L</creator><creator>Salekin, Asif</creator><creator>Xiao, Yi</creator><creator>Sharma, Harshit</creator><creator>McAllister, Tara</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>GOX</scope></search><sort><creationdate>20230525</creationdate><title>Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants</title><author>Benway, Nina R ; Preston, Jonathan L ; Salekin, Asif ; Xiao, Yi ; Sharma, Harshit ; McAllister, Tara</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a951-cebe05f31d3b5f65294a703ae72d702f193626e74ab4de837e89f24e4fd357f33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Age</topic><topic>Recurrent neural networks</topic><topic>Sex</topic><topic>Speech sounds</topic><toplevel>online_resources</toplevel><creatorcontrib>Benway, Nina R</creatorcontrib><creatorcontrib>Preston, Jonathan L</creatorcontrib><creatorcontrib>Salekin, Asif</creatorcontrib><creatorcontrib>Xiao, Yi</creatorcontrib><creatorcontrib>Sharma, Harshit</creatorcontrib><creatorcontrib>McAllister, Tara</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Benway, Nina R</au><au>Preston, Jonathan L</au><au>Salekin, Asif</au><au>Xiao, Yi</au><au>Sharma, Harshit</au><au>McAllister, Tara</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants</atitle><jtitle>arXiv.org</jtitle><date>2023-05-25</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g., /r/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic /r/ in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score =.81 ({\sigma}x=.10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2305.16111</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-05
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2305_16111
source arXiv.org; Free E- Journals
subjects Age
Recurrent neural networks
Sex
Speech sounds
title Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T11%3A04%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Classifying%20Rhoticity%20of%20/r/%20in%20Speech%20Sound%20Disorder%20using%20Age-and-Sex%20Normalized%20Formants&rft.jtitle=arXiv.org&rft.au=Benway,%20Nina%20R&rft.date=2023-05-25&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2305.16111&rft_dat=%3Cproquest_arxiv%3E2819557378%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2819557378&rft_id=info:pmid/&rfr_iscdi=true