Loading…
Investigation of Different Time-Frequency Representations for Intelligibility Assessment of Dysarthric Speech
Speech disorders linked to neurological problems affect person's ability to communicate through speech. Dysarthria is one of the speech disorders caused due to muscle weakness producing slow, slurred and less intelligible speech. Automatic intelligibility assessment of dysarthria from speech ca...
Saved in:
| Published in: | IEEE transactions on neural systems and rehabilitation engineering 2020-12, Vol.28 (12), p.2880-2889 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3 |
| container_end_page | 2889 |
| container_issue | 12 |
| container_start_page | 2880 |
| container_title | IEEE transactions on neural systems and rehabilitation engineering |
| container_volume | 28 |
| creator | H M, Chandrashekar Karjigi, Veena Sreedevi, N |
| description | Speech disorders linked to neurological problems affect person's ability to communicate through speech. Dysarthria is one of the speech disorders caused due to muscle weakness producing slow, slurred and less intelligible speech. Automatic intelligibility assessment of dysarthria from speech can be used as a promising clinical tool in treatment. This paper explores the use of perceptually enhanced Fourier transform spectrograms and Constant-Q transform spectrograms with CNN to assess word level and sentence level intelligibility of dysarthric speech from UA and TORGO databases. Constant-Q transform and perceptually enhanced mel warped STFT spectrograms performed better in the classification task. |
| doi_str_mv | 10.1109/TNSRE.2020.3035392 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_miscellaneous_2457650884</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9247264</ieee_id><sourcerecordid>2483254896</sourcerecordid><originalsourceid>FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3</originalsourceid><addsrcrecordid>eNpdkUtPwkAUhSdGI4j-AU1MEzduindefSwJgpIQTQDXTTu9hSG0xZliwr93CsjC1UzmfufkzD2E3FPoUwrxy-JjPhv1GTDoc-CSx-yCdKmUkQ-MwmV758IXnEGH3Fi7BqBhIMNr0uGcChqEvEvKSfWDttHLtNF15dWF96qLAg1WjbfQJfpjg987rNTem-HWoHWDA2q9ojbepGpws9FLnemNbvbewFq0tmzVrdXepqZZGa28-RZRrW7JVZFuLN6dzh75Go8Ww3d_-vk2GQ6mvuKSNn6Qx5hTKtOM81zlEchMSYAsFbFCZEIKycKMhiFzn2CxCiTE7qEIoFCMKsV75PnouzW1S2-bpNRWuaRphfXOJs7CbQKiSDj06R-6rnemcukcFXEmRRQHjmJHSpnaWoNFsjW6TM0-oZC0ZSSHMpK2jORUhhM9nqx3WYn5WfK3fQc8HAGNiOdxzETIAsF_AU1ujvE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2483254896</pqid></control><display><type>article</type><title>Investigation of Different Time-Frequency Representations for Intelligibility Assessment of Dysarthric Speech</title><source>Alma/SFX Local Collection</source><creator>H M, Chandrashekar ; Karjigi, Veena ; Sreedevi, N</creator><creatorcontrib>H M, Chandrashekar ; Karjigi, Veena ; Sreedevi, N</creatorcontrib><description>Speech disorders linked to neurological problems affect person's ability to communicate through speech. Dysarthria is one of the speech disorders caused due to muscle weakness producing slow, slurred and less intelligible speech. Automatic intelligibility assessment of dysarthria from speech can be used as a promising clinical tool in treatment. This paper explores the use of perceptually enhanced Fourier transform spectrograms and Constant-Q transform spectrograms with CNN to assess word level and sentence level intelligibility of dysarthric speech from UA and TORGO databases. Constant-Q transform and perceptually enhanced mel warped STFT spectrograms performed better in the classification task.</description><identifier>ISSN: 1534-4320</identifier><identifier>EISSN: 1558-0210</identifier><identifier>DOI: 10.1109/TNSRE.2020.3035392</identifier><identifier>PMID: 33141673</identifier><identifier>CODEN: ITNSB3</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Acoustics ; constant-Q transform ; convolutional neural networks ; Disorders ; Dysarthria ; Feature extraction ; Fourier transforms ; Intelligibility ; intelligibility assessment ; Muscles ; Neurological diseases ; perceptual enhancement ; short time Fourier transform ; Signal resolution ; single frequency filtering ; Spectrogram ; Spectrograms ; Speech ; Speech disorders ; Time-frequency analysis ; Transforms</subject><ispartof>IEEE transactions on neural systems and rehabilitation engineering, 2020-12, Vol.28 (12), p.2880-2889</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3</citedby><cites>FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3</cites><orcidid>0000-0003-3186-1762 ; 0000-0002-9268-5080 ; 0000-0002-2466-486X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33141673$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>H M, Chandrashekar</creatorcontrib><creatorcontrib>Karjigi, Veena</creatorcontrib><creatorcontrib>Sreedevi, N</creatorcontrib><title>Investigation of Different Time-Frequency Representations for Intelligibility Assessment of Dysarthric Speech</title><title>IEEE transactions on neural systems and rehabilitation engineering</title><addtitle>TNSRE</addtitle><addtitle>IEEE Trans Neural Syst Rehabil Eng</addtitle><description>Speech disorders linked to neurological problems affect person's ability to communicate through speech. Dysarthria is one of the speech disorders caused due to muscle weakness producing slow, slurred and less intelligible speech. Automatic intelligibility assessment of dysarthria from speech can be used as a promising clinical tool in treatment. This paper explores the use of perceptually enhanced Fourier transform spectrograms and Constant-Q transform spectrograms with CNN to assess word level and sentence level intelligibility of dysarthric speech from UA and TORGO databases. Constant-Q transform and perceptually enhanced mel warped STFT spectrograms performed better in the classification task.</description><subject>Acoustics</subject><subject>constant-Q transform</subject><subject>convolutional neural networks</subject><subject>Disorders</subject><subject>Dysarthria</subject><subject>Feature extraction</subject><subject>Fourier transforms</subject><subject>Intelligibility</subject><subject>intelligibility assessment</subject><subject>Muscles</subject><subject>Neurological diseases</subject><subject>perceptual enhancement</subject><subject>short time Fourier transform</subject><subject>Signal resolution</subject><subject>single frequency filtering</subject><subject>Spectrogram</subject><subject>Spectrograms</subject><subject>Speech</subject><subject>Speech disorders</subject><subject>Time-frequency analysis</subject><subject>Transforms</subject><issn>1534-4320</issn><issn>1558-0210</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNpdkUtPwkAUhSdGI4j-AU1MEzduindefSwJgpIQTQDXTTu9hSG0xZliwr93CsjC1UzmfufkzD2E3FPoUwrxy-JjPhv1GTDoc-CSx-yCdKmUkQ-MwmV758IXnEGH3Fi7BqBhIMNr0uGcChqEvEvKSfWDttHLtNF15dWF96qLAg1WjbfQJfpjg987rNTem-HWoHWDA2q9ojbepGpws9FLnemNbvbewFq0tmzVrdXepqZZGa28-RZRrW7JVZFuLN6dzh75Go8Ww3d_-vk2GQ6mvuKSNn6Qx5hTKtOM81zlEchMSYAsFbFCZEIKycKMhiFzn2CxCiTE7qEIoFCMKsV75PnouzW1S2-bpNRWuaRphfXOJs7CbQKiSDj06R-6rnemcukcFXEmRRQHjmJHSpnaWoNFsjW6TM0-oZC0ZSSHMpK2jORUhhM9nqx3WYn5WfK3fQc8HAGNiOdxzETIAsF_AU1ujvE</recordid><startdate>20201201</startdate><enddate>20201201</enddate><creator>H M, Chandrashekar</creator><creator>Karjigi, Veena</creator><creator>Sreedevi, N</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QQ</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7TK</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>NAPCQ</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0003-3186-1762</orcidid><orcidid>https://orcid.org/0000-0002-9268-5080</orcidid><orcidid>https://orcid.org/0000-0002-2466-486X</orcidid></search><sort><creationdate>20201201</creationdate><title>Investigation of Different Time-Frequency Representations for Intelligibility Assessment of Dysarthric Speech</title><author>H M, Chandrashekar ; Karjigi, Veena ; Sreedevi, N</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Acoustics</topic><topic>constant-Q transform</topic><topic>convolutional neural networks</topic><topic>Disorders</topic><topic>Dysarthria</topic><topic>Feature extraction</topic><topic>Fourier transforms</topic><topic>Intelligibility</topic><topic>intelligibility assessment</topic><topic>Muscles</topic><topic>Neurological diseases</topic><topic>perceptual enhancement</topic><topic>short time Fourier transform</topic><topic>Signal resolution</topic><topic>single frequency filtering</topic><topic>Spectrogram</topic><topic>Spectrograms</topic><topic>Speech</topic><topic>Speech disorders</topic><topic>Time-frequency analysis</topic><topic>Transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>H M, Chandrashekar</creatorcontrib><creatorcontrib>Karjigi, Veena</creatorcontrib><creatorcontrib>Sreedevi, N</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) Online</collection><collection>IEL</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Nursing & Allied Health Premium</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on neural systems and rehabilitation engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>H M, Chandrashekar</au><au>Karjigi, Veena</au><au>Sreedevi, N</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Investigation of Different Time-Frequency Representations for Intelligibility Assessment of Dysarthric Speech</atitle><jtitle>IEEE transactions on neural systems and rehabilitation engineering</jtitle><stitle>TNSRE</stitle><addtitle>IEEE Trans Neural Syst Rehabil Eng</addtitle><date>2020-12-01</date><risdate>2020</risdate><volume>28</volume><issue>12</issue><spage>2880</spage><epage>2889</epage><pages>2880-2889</pages><issn>1534-4320</issn><eissn>1558-0210</eissn><coden>ITNSB3</coden><abstract>Speech disorders linked to neurological problems affect person's ability to communicate through speech. Dysarthria is one of the speech disorders caused due to muscle weakness producing slow, slurred and less intelligible speech. Automatic intelligibility assessment of dysarthria from speech can be used as a promising clinical tool in treatment. This paper explores the use of perceptually enhanced Fourier transform spectrograms and Constant-Q transform spectrograms with CNN to assess word level and sentence level intelligibility of dysarthric speech from UA and TORGO databases. Constant-Q transform and perceptually enhanced mel warped STFT spectrograms performed better in the classification task.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>33141673</pmid><doi>10.1109/TNSRE.2020.3035392</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0003-3186-1762</orcidid><orcidid>https://orcid.org/0000-0002-9268-5080</orcidid><orcidid>https://orcid.org/0000-0002-2466-486X</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1534-4320 |
| ispartof | IEEE transactions on neural systems and rehabilitation engineering, 2020-12, Vol.28 (12), p.2880-2889 |
| issn | 1534-4320 1558-0210 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2457650884 |
| source | Alma/SFX Local Collection |
| subjects | Acoustics constant-Q transform convolutional neural networks Disorders Dysarthria Feature extraction Fourier transforms Intelligibility intelligibility assessment Muscles Neurological diseases perceptual enhancement short time Fourier transform Signal resolution single frequency filtering Spectrogram Spectrograms Speech Speech disorders Time-frequency analysis Transforms |
| title | Investigation of Different Time-Frequency Representations for Intelligibility Assessment of Dysarthric Speech |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T14%3A26%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Investigation%20of%20Different%20Time-Frequency%20Representations%20for%20Intelligibility%20Assessment%20of%20Dysarthric%20Speech&rft.jtitle=IEEE%20transactions%20on%20neural%20systems%20and%20rehabilitation%20engineering&rft.au=H%20M,%20Chandrashekar&rft.date=2020-12-01&rft.volume=28&rft.issue=12&rft.spage=2880&rft.epage=2889&rft.pages=2880-2889&rft.issn=1534-4320&rft.eissn=1558-0210&rft.coden=ITNSB3&rft_id=info:doi/10.1109/TNSRE.2020.3035392&rft_dat=%3Cproquest_ieee_%3E2483254896%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c351t-6d9ed115ab33dcd805bc500ba49cee2454527b177216729c650927bf60fc21cc3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2483254896&rft_id=info:pmid/33141673&rft_ieee_id=9247264&rfr_iscdi=true |