{"id":"https://openalex.org/W4410771614","doi":"https://doi.org/10.1109/icasspw65056.2025.11011272","title":"Pathological Voice Detection From Sustained Vowels: Handcrafted vs. Self-supervised Learning","display_name":"Pathological Voice Detection From Sustained Vowels: Handcrafted vs. Self-supervised Learning","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771614","doi":"https://doi.org/10.1109/icasspw65056.2025.11011272"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["AIST,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046057045","display_name":"Akira Sasou","orcid":"https://orcid.org/0000-0003-1700-0325"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Sasou","raw_affiliation_strings":["AIST,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.5526,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9790572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.954200029373169,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.954200029373169,"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/computer-science","display_name":"Computer science","score":0.6663805842399597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.540358304977417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333682894706726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6663805842399597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.540358304977417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333682894706726}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2046678753","https://openalex.org/W2148143831","https://openalex.org/W2239141610","https://openalex.org/W2295598076","https://openalex.org/W2321038435","https://openalex.org/W2754402200","https://openalex.org/W2787553229","https://openalex.org/W2806307414","https://openalex.org/W2884225676","https://openalex.org/W2898186885","https://openalex.org/W2920847976","https://openalex.org/W3093575194","https://openalex.org/W3196473068","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4308599792","https://openalex.org/W4312951904","https://openalex.org/W4319878709","https://openalex.org/W4383222114","https://openalex.org/W4385822292","https://openalex.org/W4402112095","https://openalex.org/W4405633023","https://openalex.org/W6760776128","https://openalex.org/W6790598508"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Pathological":[0],"voice":[1,6,26,59,147],"detection":[2,60,149],"aims":[3],"to":[4],"detect":[5],"disorders":[7],"from":[8],"speech":[9],"samples.":[10],"With":[11],"the":[12,22,114,123,130,134],"recent":[13],"development":[14],"of":[15,25,120],"self-supervised":[16],"learning":[17],"(SSL),":[18],"most":[19],"studies":[20,128],"in":[21],"past":[23],"years":[24],"disorder":[27,148],"employ":[28],"that":[29,96,140],"technique.":[30],"Handcrafted":[31],"features":[32,53,72,98,112,142,156],"may":[33],"suggest":[34],"better":[35],"prediction":[36],"since":[37],"they":[38],"contain":[39],"physical":[40],"information":[41],"and":[42,54,68,75,86,92,110,151],"are":[43,99,143],"more":[44],"interpretable":[45],"than":[46],"SSL.":[47],"We":[48,65],"evaluated":[49,82],"different":[50],"handcrafted":[51,71,97,109,141],"acoustic":[52],"SSL":[55,103,111,155],"approaches":[56],"for":[57,89,146],"pathological":[58],"tasks":[61],"using":[62,73],"sustained":[63],"vowels.":[64],"extracted":[66],"88":[67],"39":[69],"dimensional":[70],"openSMILE":[74],"Praat":[76],"feature":[77,90],"extractors.":[78],"For":[79],"SSL,":[80],"we":[81],"wav2vec":[83],"2.0,":[84],"HuBERT,":[85],"WavLM,":[87],"both":[88],"extractors":[91],"finetuning.":[93],"Results":[94],"showed":[95],"consistently":[100],"competitive":[101,145],"with":[102,117,154],"features.":[104],"An":[105],"ensemble":[106],"model":[107],"combining":[108,152],"achieved":[113],"best":[115],"performance":[116],"an":[118],"F1-score":[119],"0.8739":[121],"on":[122,129],"test":[124,135],"set,":[125],"outperforming":[126],"previous":[127],"same":[131],"dataset":[132],"under":[133],"set.":[136],"This":[137],"finding":[138],"suggests":[139],"still":[144],"tasks,":[150],"them":[153],"can":[157],"further":[158],"improve":[159],"performance.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}