{"id":"https://openalex.org/W4372338196","doi":"https://doi.org/10.1109/icassp49357.2023.10094857","title":"Wav2vec-Based Detection and Severity Level Classification of Dysarthria From Speech","display_name":"Wav2vec-Based Detection and Severity Level Classification of Dysarthria From Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338196","doi":"https://doi.org/10.1109/icassp49357.2023.10094857"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.14107","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057697917","display_name":"Farhad Javanmardi","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Farhad Javanmardi","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Finland","Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078659691","display_name":"Saska Tirronen","orcid":"https://orcid.org/0000-0002-1491-5768"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Saska Tirronen","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Finland","Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042157833","display_name":"Manila Kodali","orcid":"https://orcid.org/0000-0003-4594-4921"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manila Kodali","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Finland","Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Finland","Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Finland","Department of Signal Processing and Acoustics, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":7.3935,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.97978487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.8922743797302246},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7199817895889282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6866509914398193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178243160247803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5734195113182068},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5599420070648193},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5440245866775513},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5101137757301331},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45989754796028137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44969871640205383},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4263094663619995},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.13406729698181152},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08542579412460327},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08195766806602478}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.8922743797302246},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7199817895889282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6866509914398193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178243160247803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5734195113182068},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5599420070648193},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5440245866775513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5101137757301331},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45989754796028137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44969871640205383},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4263094663619995},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.13406729698181152},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08542579412460327},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08195766806602478},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.14107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14107","pdf_url":"https://arxiv.org/pdf/2309.14107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.14107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14107","pdf_url":"https://arxiv.org/pdf/2309.14107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372338196.pdf","grobid_xml":"https://content.openalex.org/works/W4372338196.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W2001702556","https://openalex.org/W2065840343","https://openalex.org/W2085662862","https://openalex.org/W2091380405","https://openalex.org/W2101234009","https://openalex.org/W2107570013","https://openalex.org/W2182621190","https://openalex.org/W2191779130","https://openalex.org/W2346340151","https://openalex.org/W2889443538","https://openalex.org/W2937864292","https://openalex.org/W2938626858","https://openalex.org/W2982534039","https://openalex.org/W3022666696","https://openalex.org/W3036601975","https://openalex.org/W3198786495","https://openalex.org/W3202370288","https://openalex.org/W3206041894","https://openalex.org/W4297841875","https://openalex.org/W4304087162","https://openalex.org/W6675354045","https://openalex.org/W6780218876","https://openalex.org/W6802655330"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2138847091"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,38,60],"and":[2,39],"severity":[3,40,102],"level":[4,41,103],"classification":[5,42,104],"of":[6,78,87,120],"dysarthria":[7],"directly":[8],"from":[9,74,112],"acoustic":[10],"speech":[11],"signals":[12],"can":[13],"be":[14],"used":[15,55],"as":[16,32],"a":[17,33],"tool":[18],"in":[19,89,122],"medical":[20],"diagnosis.":[21],"In":[22,58,99],"this":[23],"work,":[24],"the":[25,53,59,62,66,72,75,79,93,100,106,110,113,126],"pre-trained":[26],"wav2vec":[27,80],"2.0":[28],"model":[29,81],"is":[30],"studied":[31,101],"feature":[34,97],"extractor":[35],"to":[36,92,125],"build":[37],"systems":[43],"for":[44],"dysarthric":[45],"speech.":[46],"The":[47],"experiments":[48],"were":[49],"carried":[50],"out":[51],"with":[52],"popularly":[54],"UA-speech":[56],"database.":[57],"experiments,":[61],"results":[63,107],"revealed":[64,108],"that":[65,82,109],"best":[67,94,127],"performance":[68],"was":[69],"obtained":[70],"using":[71],"embeddings":[73,111],"first":[76],"layer":[77,115],"yielded":[83],"an":[84,117],"absolute":[85,118],"improvement":[86,119],"1.23%":[88],"accuracy":[90,123],"compared":[91,124],"performing":[95],"baseline":[96,128],"(spectrogram).":[98],"task,":[105],"final":[114],"gave":[116],"10.62%":[121],"features":[129],"(mel-frequency":[130],"cepstral":[131],"coefficients).":[132]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2023-05-07T00:00:00"}
