{"id":"https://openalex.org/W4414893707","doi":"https://doi.org/10.21437/interspeech.2025-2373","title":"Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches","display_name":"Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414893707","doi":"https://doi.org/10.21437/interspeech.2025-2373"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2373","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.00853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031540690","display_name":"Dena F. Mujtaba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dena Mujtaba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108624212","display_name":"Nihar R. Mahapatra","orcid":"https://orcid.org/0000-0002-3821-3330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nihar R. Mahapatra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2795,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92993934,"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":"3568","last_page":"3572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9934999942779541,"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/T12031","display_name":"Speech and dialogue systems","score":0.9934999942779541,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9873999953269958,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.9868999719619751,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stuttering","display_name":"Stuttering","score":0.8342000246047974},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6682000160217285},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.515999972820282},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3012000024318695}],"concepts":[{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.8342000246047974},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6682000160217285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6442000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212000250816345},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36239999532699585},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.2955000102519989},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2373","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.00853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00853","pdf_url":"https://arxiv.org/pdf/2506.00853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.00853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00853","pdf_url":"https://arxiv.org/pdf/2506.00853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Stuttering":[0],"--":[1,12],"characterized":[2],"by":[3,16,50],"involuntary":[4],"disfluencies":[5,40],"such":[6],"as":[7],"blocks,":[8],"prolongations,":[9],"and":[10,28,43,91],"repetitions":[11],"is":[13],"often":[14],"misinterpreted":[15],"automatic":[17],"speech":[18,54,79],"recognition":[19],"(ASR)":[20],"systems,":[21],"resulting":[22],"in":[23,113],"elevated":[24],"word":[25,109],"error":[26,110],"rates":[27],"making":[29],"voice-driven":[30],"technologies":[31],"inaccessible":[32],"to":[33,73,77],"people":[34],"who":[35],"stutter.":[36],"The":[37],"variability":[38],"of":[39,85,119],"across":[41,70],"speakers":[42],"contexts":[44],"further":[45],"complicates":[46],"ASR":[47],"training,":[48],"compounded":[49],"limited":[51],"annotated":[52],"stuttered":[53,64],"data.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,94],"investigate":[60],"fine-tuning":[61],"ASRs":[62,106],"for":[63,122],"speech,":[65,115],"comparing":[66],"generalized":[67],"models":[68,75,121],"(trained":[69],"multiple":[71],"speakers)":[72],"personalized":[74,105],"tailored":[76,120],"individual":[78],"characteristics.":[80],"Using":[81],"a":[82],"diverse":[83],"range":[84],"voice-AI":[86],"scenarios,":[87],"including":[88],"virtual":[89],"assistants":[90],"video":[92],"interviews,":[93],"evaluate":[95],"how":[96],"personalization":[97],"affects":[98],"transcription":[99],"accuracy.":[100],"Our":[101],"findings":[102],"show":[103],"that":[104],"significantly":[107],"reduce":[108],"rates,":[111],"especially":[112],"spontaneous":[114],"highlighting":[116],"the":[117],"potential":[118],"more":[123],"inclusive":[124],"voice":[125],"technologies.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}