{"id":"https://openalex.org/W4406461753","doi":"https://doi.org/10.1109/slt61566.2024.10832349","title":"Augmenting Automatic Speech Recognition Models With Disfluency Detection","display_name":"Augmenting Automatic Speech Recognition Models With Disfluency Detection","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461753","doi":"https://doi.org/10.1109/slt61566.2024.10832349"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832349","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":"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":null,"display_name":"Robin Amann","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robin Amann","raw_affiliation_strings":["Karlsruhe Institute of Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675929","display_name":"Zhaolin Li","orcid":"https://orcid.org/0000-0002-5980-0315"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhaolin Li","raw_affiliation_strings":["Karlsruhe Institute of Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039847272","display_name":"Barbara Bruno","orcid":"https://orcid.org/0000-0003-0953-7173"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Barbara Bruno","raw_affiliation_strings":["Karlsruhe Institute of Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046084081","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0002-4231-6543"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":["Karlsruhe Institute of Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68476718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"224","last_page":"231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8022805452346802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7170877456665039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46672335267066956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4581351578235626},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4357905983924866},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34959083795547485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022805452346802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7170877456665039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46672335267066956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4581351578235626},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4357905983924866},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34959083795547485}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832349","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2107092366","https://openalex.org/W2753392522","https://openalex.org/W2962780374","https://openalex.org/W3036601975","https://openalex.org/W3043783436","https://openalex.org/W3167533889","https://openalex.org/W3175745257","https://openalex.org/W3197433369","https://openalex.org/W3198298452","https://openalex.org/W4221147660","https://openalex.org/W4221149170","https://openalex.org/W4224917162","https://openalex.org/W4225369246","https://openalex.org/W4280509456","https://openalex.org/W4289912316","https://openalex.org/W4296068429","https://openalex.org/W4296068599","https://openalex.org/W4366547420","https://openalex.org/W4366549322","https://openalex.org/W4372260522","https://openalex.org/W4372266801","https://openalex.org/W4385822647","https://openalex.org/W4385987638","https://openalex.org/W4391021769","https://openalex.org/W4402111741","https://openalex.org/W4402112517","https://openalex.org/W6780218876","https://openalex.org/W6809739816","https://openalex.org/W6810467415","https://openalex.org/W6847363464","https://openalex.org/W6880960514"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W191108438","https://openalex.org/W3135230428","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":{"Speech":[0,12],"disfluency":[1],"commonly":[2],"occurs":[3],"in":[4,45],"conversational":[5],"and":[6,43,55,140,154],"spontaneous":[7],"speech.":[8,47,114],"However,":[9],"standard":[10],"Automatic":[11],"Recognition":[13],"(ASR)":[14],"models":[15,86],"struggle":[16],"to":[17,69,77,106,120],"accurately":[18],"recognize":[19],"these":[20],"disfluencies":[21,36],"because":[22],"they":[23],"are":[24],"typically":[25],"trained":[26],"on":[27,34,156],"fluent":[28],"transcripts.":[29],"Current":[30],"research":[31],"mainly":[32],"focuses":[33],"detecting":[35],"within":[37],"transcripts,":[38],"overlooking":[39],"their":[40],"exact":[41],"location":[42],"duration":[44],"the":[46,75,147,168,175,178],"Additionally,":[48,115],"previous":[49],"work":[50,94],"often":[51],"requires":[52],"model":[53,73,119,134],"fine-tuning":[54],"addresses":[56],"limited":[57],"types":[58],"of":[59,138,143,150,167,180],"disfluencies.":[60,80,91],"In":[61],"this":[62,93,181],"work,":[63],"we":[64,116,164],"present":[65],"an":[66,136,141],"inference-only":[67],"approach":[68],"augment":[70],"any":[71],"ASR":[72,85],"with":[74],"ability":[76],"detect":[78],"open-set":[79],"We":[81,145],"first":[82],"demonstrate":[83],"that":[84,163,170],"have":[87],"difficulty":[88],"transcribing":[89],"speech":[90,130],"Next,":[92],"proposes":[95],"a":[96,118,157],"modified":[97],"Connectionist":[98],"Temporal":[99],"Classification(CTC)based":[100],"forced":[101],"alignment":[102,122,151],"algorithm":[103],"from":[104],"[1]":[105],"predict":[107],"wordlevel":[108],"timestamps":[109,125],"while":[110],"effectively":[111],"capturing":[112],"disfluent":[113,129,158],"develop":[117],"classify":[121],"gaps":[123],"between":[124],"as":[126],"either":[127],"containing":[128],"or":[131],"silence.":[132],"This":[133],"achieves":[135],"accuracy":[137],"81.62%":[139],"F1-score":[142],"80.07%.":[144],"test":[146],"augmentation":[148],"pipeline":[149,182],"gap":[152],"detection":[153],"classification":[155],"dataset.":[159],"Our":[160],"results":[161],"show":[162],"captured":[165],"74.13%":[166],"words":[169],"were":[171],"initially":[172],"missed":[173],"by":[174],"transcription,":[176],"demonstrating":[177],"potential":[179],"for":[183],"downstream":[184],"tasks.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}