{"id":"https://openalex.org/W4415433100","doi":"https://doi.org/10.21437/interspeech.2025-2193","title":"Enhancing Transcripts of Open-Source Automatic Speech Recognition Models Through Fine-Tuning with Laughter and Speech-Laugh","display_name":"Enhancing Transcripts of Open-Source Automatic Speech Recognition Models Through Fine-Tuning with Laughter and Speech-Laugh","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433100","doi":"https://doi.org/10.21437/interspeech.2025-2193"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2193","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.utwente.nl/en/publications/f20bccf6-a968-4642-ae87-862a7ffd94ae","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028157891","display_name":"Perry Ho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phuoc Hoang Ho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054202617","display_name":"D. Balan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Drago\u0219 Alexandru B\u0103lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091409488","display_name":"Dirk Heylen","orcid":"https://orcid.org/0000-0003-4288-3334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dirk K. J. Heylen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068294985","display_name":"Khiet P. Truong","orcid":"https://orcid.org/0000-0002-7243-0523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khiet P. Truong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14163346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4513","last_page":"4517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8658999800682068,"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":0.8658999800682068,"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/laughter","display_name":"Laughter","score":0.4207000136375427},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.30970001220703125},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.29899999499320984},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.2948000133037567},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2892000079154968}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.60589998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5436000227928162},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3165999948978424},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2890999913215637}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2193","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:ris.utwente.nl:openaire/f20bccf6-a968-4642-ae87-862a7ffd94ae","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/f20bccf6-a968-4642-ae87-862a7ffd94ae","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ho, P H, B\u0103lan, D A, Heylen, D K J & Truong, K P 2025, Enhancing Transcripts of Open-Source Automatic Speech Recognition Models Through Fine-Tuning with Laughter and Speech-Laugh. in Interspeech 2025. pp. 4513-4517, 26th Interspeech 2025, Rotterdam, Netherlands, 17/08/25. https://doi.org/10.21437/Interspeech.2025-2193","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire/f20bccf6-a968-4642-ae87-862a7ffd94ae","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/f20bccf6-a968-4642-ae87-862a7ffd94ae","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ho, P H, B\u0103lan, D A, Heylen, D K J & Truong, K P 2025, Enhancing Transcripts of Open-Source Automatic Speech Recognition Models Through Fine-Tuning with Laughter and Speech-Laugh. in Interspeech 2025. pp. 4513-4517, 26th Interspeech 2025, Rotterdam, Netherlands, 17/08/25. https://doi.org/10.21437/Interspeech.2025-2193","raw_type":"info:eu-repo/semantics/publishedVersion"},"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":{"Non-lexical":[0],"sounds":[1,14],"such":[2],"as":[3,12,61,95],"laughter":[4,56,84,110],"are":[5,41,82],"considered":[6],"important":[7],"discourse":[8],"markers":[9],"in":[10,19,27,54,67,114],"conversation":[11],"these":[13,46],"complement":[15],"the":[16,24,68],"lexical":[17],"information":[18],"shaping":[20],"interpersonal":[21],"relations,":[22],"managing":[23],"conversation,":[25],"and":[26,30,64,85,93,101,104],"expressing":[28],"attitudes":[29],"affect.":[31],"However,":[32],"general":[33],"purpose":[34],"open-source":[35,79],"automatic":[36],"speech":[37,97],"recognition":[38],"(ASR)":[39],"systems":[40],"typically":[42],"not":[43,59],"focusing":[44],"on":[45],"sounds.":[47],"Laughter":[48],"transcription":[49],"is":[50,57,65],"an":[51],"understudied":[52],"task":[53],"ASR:":[55],"often":[58],"modelled":[60],"a":[62],"token":[63],"discarded":[66],"evaluation":[69],"of":[70],"ASR.":[71],"In":[72],"our":[73],"study,":[74],"we":[75,99],"investigate":[76],"how":[77],"current":[78],"ASR":[80,115],"models":[81],"handling":[83],"speech-laugh":[86],"(speech":[87],"interspersed":[88],"with":[89],"laughter).":[90],"Using":[91],"Switchboard":[92],"BuckEye":[94],"conversational":[96],"corpora,":[98],"fine-tuned":[100],"evaluated":[102],"Whisper":[103],"Wav2Vec2.":[105],"Our":[106],"results":[107],"show":[108],"that":[109],"can":[111],"be":[112],"integrated":[113],"transcriptions":[116],"without":[117],"substantially":[118],"degrading":[119],"word":[120],"error":[121],"rate.<br/>":[122]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}