{"id":"https://openalex.org/W4372267351","doi":"https://doi.org/10.1109/icassp49357.2023.10095629","title":"Toward A Multimodal Approach for Disfluency Detection and Categorization","display_name":"Toward A Multimodal Approach for Disfluency Detection and Categorization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267351","doi":"https://doi.org/10.1109/icassp49357.2023.10095629"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095629","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":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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","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,Computer Science and Engineering,Ann Arbor,Michigan,USA","Microsoft Corporation, Redmond, Washington, USA","Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Computer Science and Engineering,Ann Arbor,Michigan,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","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,Washington,USA","Microsoft Corporation, Redmond, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,Washington,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035651773"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":1.2811,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78801144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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/T12684","display_name":"Stuttering Research and Treatment","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9944999814033508,"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":0.8314080238342285},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7869600057601929},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5859431624412537},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5717911124229431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002346038818359},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4969647228717804},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47197777032852173},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42449235916137695},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10583987832069397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314080238342285},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7869600057601929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5859431624412537},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5717911124229431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002346038818359},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4969647228717804},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47197777032852173},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42449235916137695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10583987832069397},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095629","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W195165228","https://openalex.org/W1968936448","https://openalex.org/W2018453254","https://openalex.org/W2161051082","https://openalex.org/W2166637769","https://openalex.org/W2794511405","https://openalex.org/W2889320445","https://openalex.org/W2963341956","https://openalex.org/W2972328063","https://openalex.org/W2973194065","https://openalex.org/W2979826702","https://openalex.org/W3033127073","https://openalex.org/W3036601975","https://openalex.org/W3161639065","https://openalex.org/W3197142850","https://openalex.org/W3197433369","https://openalex.org/W3198846836","https://openalex.org/W4295312788","https://openalex.org/W4297841747","https://openalex.org/W4297841828","https://openalex.org/W4301410255","https://openalex.org/W4361994820","https://openalex.org/W6631362777","https://openalex.org/W6766978945","https://openalex.org/W6774879280","https://openalex.org/W6780218876","https://openalex.org/W6809829207"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Speech":[0],"disfluencies,":[1],"such":[2],"as":[3,22],"filled":[4],"pauses,":[5],"repetitions,":[6],"or":[7],"revisions,":[8],"disrupt":[9],"the":[10,40,71,83,109,128,146,154],"typical":[11],"flow":[12],"of":[13,42,75,85,113],"speech.":[14],"Disfluency":[15],"detection":[16,46,94,136],"and":[17,47,73,95,111,116,137,144],"categorization":[18,48,138],"has":[19,30,49],"gained":[20],"traction":[21],"a":[23,122],"research":[24],"area":[25],"because":[26],"modeling":[27],"disfluent":[28],"events":[29],"been":[31],"shown":[32,63],"to":[33],"be":[34],"helpful":[35],"for":[36,92],"downstream":[37],"tasks.":[38],"However,":[39],"majority":[41],"work":[43],"on":[44,51],"disfluency":[45,93,135],"focused":[50],"language-based":[52,155],"approaches":[53],"that":[54,126,133,145],"process":[55],"manually":[56,67],"transcribed":[57,68],"text.":[58],"While":[59],"these":[60,76],"methods":[61],"have":[62],"high":[64],"accuracy,":[65],"requiring":[66],"text":[69],"limits":[70],"scalability":[72],"practicality":[74],"approaches.":[77],"In":[78],"this":[79,118],"paper,":[80],"we":[81,98,120],"evaluate":[82],"impact":[84],"using":[86,140],"automatic":[87],"speech":[88],"recognition":[89],"(ASR)":[90],"transcripts":[91],"categorization.":[96],"Additionally,":[97],"explore":[99],"skipping":[100],"transcription":[101],"altogether":[102],"with":[103],"an":[104],"acoustic":[105],"approach.":[106],"We":[107,131],"assess":[108],"strengths":[110],"weaknesses":[112],"each":[114],"modality,":[115,143],"in":[117,148],"paper":[119],"introduce":[121],"model":[123,156],"fusion":[124],"approach":[125],"combines":[127],"two":[129],"modalities.":[130],"find":[132],"multimodal":[134],"outperforms":[139],"either":[141],"individual":[142],"improvement":[147],"performance":[149],"is":[150],"especially":[151],"significant":[152],"when":[153],"processes":[157],"ASR":[158],"transcripts.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}