{"id":"https://openalex.org/W4406461996","doi":"https://doi.org/10.1109/slt61566.2024.10832220","title":"Self-Supervised Speech Models For Word-Level Stuttered Speech Detection","display_name":"Self-Supervised Speech Models For Word-Level Stuttered Speech Detection","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461996","doi":"https://doi.org/10.1109/slt61566.2024.10832220"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053466746","display_name":"Yi-Jen Shih","orcid":"https://orcid.org/0000-0003-3481-3117"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Jen Shih","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016538481","display_name":"Zoi Gkalitsiou","orcid":"https://orcid.org/0000-0002-0353-8485"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoi Gkalitsiou","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014141359","display_name":"Alexandros G. Dimakis","orcid":"https://orcid.org/0000-0002-4244-7033"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros G. Dimakis","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":4.2602,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95205479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"937","last_page":"944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/speech-recognition","display_name":"Speech recognition","score":0.7339689135551453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7189716100692749},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5284262299537659},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4725323021411896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43589895963668823},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4217422902584076},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36448127031326294},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16076913475990295}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7339689135551453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189716100692749},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5284262299537659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4725323021411896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43589895963668823},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4217422902584076},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36448127031326294},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16076913475990295},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1583837637","https://openalex.org/W1972163875","https://openalex.org/W2021694086","https://openalex.org/W2040774889","https://openalex.org/W2079075205","https://openalex.org/W2084274775","https://openalex.org/W2344206449","https://openalex.org/W2415242599","https://openalex.org/W2612560781","https://openalex.org/W2746963436","https://openalex.org/W2794511405","https://openalex.org/W2914304175","https://openalex.org/W3161639065","https://openalex.org/W3176579494","https://openalex.org/W3197580070","https://openalex.org/W3198298452","https://openalex.org/W3209984917","https://openalex.org/W4287173589","https://openalex.org/W4296068429","https://openalex.org/W4297841747","https://openalex.org/W4319862670","https://openalex.org/W4372266902","https://openalex.org/W4372337800","https://openalex.org/W4372338196","https://openalex.org/W4385823031","https://openalex.org/W4391021769","https://openalex.org/W4402112390","https://openalex.org/W6780218876","https://openalex.org/W6795952400","https://openalex.org/W6810007534","https://openalex.org/W6811438045","https://openalex.org/W6847363464","https://openalex.org/W6880960514"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2296205523","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Clinical":[0],"diagnosis":[1],"of":[2,34,117,167,177],"stuttering":[3,25,93,118,138,157],"requires":[4,18],"an":[5,163],"assessment":[6],"by":[7],"a":[8,31,92,127,136],"licensed":[9],"speech-language":[10,35],"pathologist.":[11],"However,":[12],"this":[13,99,123],"process":[14],"is":[15,46,108,119],"time-consuming":[16],"and":[17,22,26,69,79,134],"clinicians":[19],"with":[20,41,82,91,131],"training":[21],"experience":[23],"in":[24,98,155],"fluency":[27],"disorders.":[28],"Unfortunately,":[29],"only":[30],"small":[32],"percentage":[33],"pathologists":[36,76],"report":[37],"being":[38],"comfortable":[39],"working":[40],"individuals":[42,54],"who":[43,55,84],"stutter,":[44],"which":[45,107],"inadequate":[47],"to":[48,77,88],"accommodate":[49],"for":[50,62,72,111,182],"the":[51,120,173],"80":[52],"million":[53],"stutter":[56],"worldwide.":[57],"Developing":[58],"machine":[59],"learning":[60],"models":[61,181],"detecting":[63],"stuttered":[64,128,183],"speech":[65,75,94,129,139,144,158,180,184],"would":[66],"enable":[67],"universal":[68],"automated":[70],"screening":[71],"stuttering,":[73],"enabling":[74],"identify":[78],"follow":[80],"up":[81],"patients":[83],"are":[85],"most":[86,174],"likely":[87],"be":[89],"diagnosed":[90],"disorder.":[95],"Previous":[96],"research":[97],"area":[100],"has":[101],"predominantly":[102],"focused":[103],"on":[104],"utterance-level":[105],"detection,":[106],"not":[109],"sufficient":[110],"clinical":[112],"settings":[113],"where":[114],"word-level":[115,132,137,156],"annotation":[116],"norm.":[121],"In":[122],"study,":[124],"we":[125,161],"curated":[126],"dataset":[130],"annotations":[133],"introduced":[135],"detection":[140],"model":[141,151],"leveraging":[142],"self-supervised":[143,179],"models.":[145],"Our":[146],"evaluation":[147],"demonstrates":[148],"that":[149],"our":[150,168],"surpasses":[152],"previous":[153],"approaches":[154],"detection.":[159,185],"Additionally,":[160],"conducted":[162],"extensive":[164],"ablation":[165],"analysis":[166],"method,":[169],"providing":[170],"insight":[171],"into":[172],"important":[175],"aspects":[176],"adapting":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
