{"id":"https://openalex.org/W4403674676","doi":"https://doi.org/10.1109/taslp.2024.3485465","title":"Automatic Disfluency Detection From Untranscribed Speech","display_name":"Automatic Disfluency Detection From Untranscribed Speech","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403674676","doi":"https://doi.org/10.1109/taslp.2024.3485465"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3485465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3485465","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5035651773","display_name":"Amrit Romana","orcid":"https://orcid.org/0009-0005-2360-0732"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amrit Romana","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0009-0005-2360-0732","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3111-5375","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003136334","display_name":"Emily Mower Provost","orcid":"https://orcid.org/0000-0003-1870-6063"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Mower Provost","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0003-1870-6063","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035651773"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":2.9802,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92380376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4727","last_page":"4740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9435999989509583,"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":0.9435999989509583,"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":0.6861125230789185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.622400164604187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44655105471611023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3528065085411072}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6861125230789185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.622400164604187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44655105471611023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3528065085411072}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3485465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3485465","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1103818213","display_name":null,"funder_award_id":"NSF IIS-RI 2006618","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W9486812","https://openalex.org/W195165228","https://openalex.org/W1494198834","https://openalex.org/W1968936448","https://openalex.org/W1979702444","https://openalex.org/W2018453254","https://openalex.org/W2021208044","https://openalex.org/W2052666245","https://openalex.org/W2107092366","https://openalex.org/W2127141656","https://openalex.org/W2127305722","https://openalex.org/W2161051082","https://openalex.org/W2165758561","https://openalex.org/W2166637769","https://openalex.org/W2293765256","https://openalex.org/W2400986993","https://openalex.org/W2404213971","https://openalex.org/W2406344726","https://openalex.org/W2803039862","https://openalex.org/W2889320445","https://openalex.org/W2896457183","https://openalex.org/W2956393827","https://openalex.org/W2963212250","https://openalex.org/W2963729456","https://openalex.org/W2964172015","https://openalex.org/W2970557265","https://openalex.org/W2972328063","https://openalex.org/W2973194065","https://openalex.org/W2979826702","https://openalex.org/W2979860911","https://openalex.org/W2996888978","https://openalex.org/W3010115535","https://openalex.org/W3033127073","https://openalex.org/W3128376221","https://openalex.org/W3136524425","https://openalex.org/W3160528423","https://openalex.org/W3197142850","https://openalex.org/W3197433369","https://openalex.org/W3197771105","https://openalex.org/W3208743843","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4297841747","https://openalex.org/W4297841828","https://openalex.org/W4366547420","https://openalex.org/W4372267351","https://openalex.org/W4385245566","https://openalex.org/W6629294717","https://openalex.org/W6633392917","https://openalex.org/W6640090968","https://openalex.org/W6679855610","https://openalex.org/W6714423078","https://openalex.org/W6752756761","https://openalex.org/W6766978945","https://openalex.org/W6774879280","https://openalex.org/W6780218876","https://openalex.org/W6791023918","https://openalex.org/W6791904447","https://openalex.org/W6847363464","https://openalex.org/W6856929521"],"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/W3204019825"],"abstract_inverted_index":{"Speech":[0],"disfluencies,":[1,106],"such":[2],"as":[3,54,87,118,153],"filled":[4],"pauses":[5],"or":[6,36],"repetitions,":[7],"are":[8],"disruptions":[9],"in":[10,99],"the":[11,23,136,158,175,191],"typical":[12],"flow":[13],"of":[14,50,81,101,138,205],"speech.":[15],"All":[16],"speakers":[17],"experience":[18],"disfluencies":[19,29,40],"at":[20,25],"times,":[21],"and":[22,53,70,78,140,188],"rate":[24],"which":[26,167],"we":[27,66,91,163,168],"produce":[28],"may":[30],"be":[31,45],"increased":[32],"by":[33,135],"certain":[34],"speaker":[35],"environmental":[37],"characteristics.":[38],"Modeling":[39],"has":[41,59],"been":[42],"shown":[43],"to":[44,104,120],"useful":[46],"for":[47,73,184],"a":[48,55,121,203],"range":[49,204],"downstream":[51],"tasks,":[52],"result,":[56],"disfluency":[57,76,109,123,129,171,187,200],"detection":[58,77,124,130,172,201],"many":[60],"potential":[61],"applications.":[62,206],"In":[63,190],"this":[64,179,194],"work,":[65],"investigate":[67],"language,":[68],"acoustic,":[69],"multimodal":[71,165],"methods":[72,83],"frame-level":[74,186],"automatic":[75,94,185,199],"categorization.":[79,189],"Each":[80],"these":[82,115],"relies":[84],"on":[85],"audio":[86],"an":[88,145,154],"input.":[89],"First,":[90],"evaluate":[92],"several":[93],"speech":[95],"recognition":[96],"(ASR)":[97],"systems":[98],"terms":[100],"their":[102],"ability":[103],"transcribe":[105],"measured":[107],"using":[108],"error":[110],"rates.":[111],"We":[112,126,142],"then":[113],"use":[114],"ASR":[116,159],"transcripts":[117,139],"input":[119],"language-based":[122],"model.":[125],"find":[127,143,169],"that":[128,144,148],"performance":[131,173],"is":[132],"largely":[133],"limited":[134],"quality":[137],"alignments.":[141],"acoustic-based":[146],"approach":[147],"does":[149],"not":[150],"require":[151],"transcription":[152],"intermediate":[155],"step":[156],"outperforms":[157],"language":[160],"approach.":[161],"Finally,":[162],"present":[164],"architectures":[166],"improve":[170],"over":[174],"unimodal":[176],"approaches.":[177],"Ultimately,":[178],"work":[180],"introduces":[181],"novel":[182],"approaches":[183],"long":[192],"term,":[193],"will":[195],"help":[196],"researchers":[197],"incorporate":[198],"into":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}