{"id":"https://openalex.org/W4372338343","doi":"https://doi.org/10.1109/icassp49357.2023.10094798","title":"Utilizing Wav2Vec In Database-Independent Voice Disorder Detection","display_name":"Utilizing Wav2Vec In Database-Independent Voice Disorder Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338343","doi":"https://doi.org/10.1109/icassp49357.2023.10094798"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094798","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/5359d163-a7c8-40a6-8910-d3311a4a212b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 Information and Communications Engineering,Finland","Department of Information and Communications Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","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 Information and Communications Engineering,Finland","Department of Information and Communications Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, 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 Information and Communications Engineering,Finland","Department of Information and Communications Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, 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 Information and Communications Engineering,Finland","Department of Information and Communications Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, 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 Information and Communications Engineering,Finland","Department of Information and Communications Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, 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":3.1217,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92169161,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166885375976562},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.7946697473526001},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6682388782501221},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6168098449707031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6164240837097168},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.601177453994751},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5536624789237976},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5372362732887268},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5074004530906677},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.503593385219574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43418222665786743},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28888165950775146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166885375976562},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7946697473526001},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6682388782501221},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6168098449707031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6164240837097168},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.601177453994751},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5536624789237976},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5372362732887268},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5074004530906677},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.503593385219574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43418222665786743},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28888165950775146},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094798","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:aaltodoc.aalto.fi:123456789/125421","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/5359d163-a7c8-40a6-8910-d3311a4a212b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/125421","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/5359d163-a7c8-40a6-8910-d3311a4a212b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W152409035","https://openalex.org/W2093190178","https://openalex.org/W2122044087","https://openalex.org/W2132025473","https://openalex.org/W2609527102","https://openalex.org/W2738314890","https://openalex.org/W2798571323","https://openalex.org/W2807317037","https://openalex.org/W2898186885","https://openalex.org/W3014647115","https://openalex.org/W3036601975","https://openalex.org/W3106436761","https://openalex.org/W3114255369","https://openalex.org/W3161627112","https://openalex.org/W3198298452","https://openalex.org/W3198786495","https://openalex.org/W3202370288","https://openalex.org/W3206041894","https://openalex.org/W3211224152","https://openalex.org/W4224930829","https://openalex.org/W4281565235","https://openalex.org/W4286841926","https://openalex.org/W4297841331","https://openalex.org/W4297841875","https://openalex.org/W4304087162","https://openalex.org/W4319862480","https://openalex.org/W4322714819","https://openalex.org/W6780218876","https://openalex.org/W6801528457","https://openalex.org/W6802655330","https://openalex.org/W6803378298","https://openalex.org/W6810936317"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W410723623","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/W2138847091","https://openalex.org/W1941834444"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,38,53,77],"of":[2,14,88,109],"voice":[3,80,102],"disorders":[4],"from":[5,32,84],"acoustic":[6],"speech":[7,23],"signals":[8,24],"can":[9,29,51],"help":[10],"to":[11,63,74,118,122],"improve":[12],"reliability":[13],"medical":[15],"diagnosis.":[16],"However,":[17],"the":[18,33,37,48,85,89,107,110,132],"real-life":[19],"environment":[20,34],"in":[21,35,55,101,113],"which":[22,36],"are":[25,99],"recorded":[26],"for":[27,79],"diagnosis":[28],"be":[30],"different":[31],"system\u2019s":[39],"training":[40],"data":[41],"was":[42],"originally":[43],"collected.":[44],"This":[45],"mismatch":[46],"between":[47],"recording":[49,126],"conditions":[50],"decrease":[52],"performance":[54,108],"practical":[56],"scenarios.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"propose":[62],"use":[64],"a":[65,71],"pre-trained":[66],"wav2vec":[67,111,133],"2.0":[68],"model":[69],"as":[70],"feature":[72],"extractor":[73],"build":[75],"automatic":[76],"systems":[78],"disorders.":[81],"The":[82,128],"embeddings":[83],"first":[86],"layers":[87],"context":[90],"network":[91],"contain":[92],"information":[93],"about":[94],"phones,":[95],"and":[96,115,125,140],"these":[97],"features":[98,112,134],"useful":[100],"disorder":[103],"detection.":[104],"We":[105],"evaluate":[106],"single-database":[114],"crossdatabase":[116],"scenarios":[117],"study":[119],"their":[120],"generalizability":[121],"unseen":[123],"speakers":[124],"conditions.":[127],"results":[129],"indicate":[130],"that":[131],"generalize":[135],"better":[136],"than":[137],"popular":[138],"spectral":[139],"cepstral":[141],"baseline":[142],"features.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
