{"id":"https://openalex.org/W4415399298","doi":"https://doi.org/10.1109/icdl63968.2025.11204445","title":"Assessing Whisper for Infant Research: Benchmarking ASR Accuracy and Failure Analysis on Caregiver-Infant Interactions","display_name":"Assessing Whisper for Infant Research: Benchmarking ASR Accuracy and Failure Analysis on Caregiver-Infant Interactions","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415399298","doi":"https://doi.org/10.1109/icdl63968.2025.11204445"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","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/A5102985014","display_name":"Yueyan Tang","orcid":"https://orcid.org/0000-0002-6521-8604"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yueyan Tang","raw_affiliation_strings":["University of California San Diego,Department of Cognitive Science,La Jolla,United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Cognitive Science,La Jolla,United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018721882","display_name":"Victoria Hennessy","orcid":"https://orcid.org/0009-0004-2739-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victoria Hennessy","raw_affiliation_strings":["University of California San Diego,Department of Cognitive Science,La Jolla,United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Cognitive Science,La Jolla,United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101803488","display_name":"Tairan Liu","orcid":"https://orcid.org/0000-0001-6157-425X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tairan Liu","raw_affiliation_strings":["University of California San Diego,Department of Cognitive Science,La Jolla,United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Cognitive Science,La Jolla,United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001354564","display_name":"Gedeon O. De\u00e1k","orcid":"https://orcid.org/0000-0001-8656-8796"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gedeon De\u00e1k","raw_affiliation_strings":["University of California San Diego,Department of Cognitive Science,La Jolla,United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Cognitive Science,La Jolla,United States","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102985014"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":2.7802,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92095326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.6306999921798706,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T12268","display_name":"Deception detection and forensic psychology","score":0.6306999921798706,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T14437","display_name":"Ethics and Legal Issues in Pediatric Healthcare","score":0.5777000188827515,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10582","display_name":"Ethics in Clinical Research","score":0.5230000019073486,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7592999935150146},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5576000213623047},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5493000149726868},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4580000042915344},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45660001039505005},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42809998989105225},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4108000099658966},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.39570000767707825}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409999966621399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.66839998960495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.3677999973297119},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25369998812675476},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1945005118","https://openalex.org/W1995766908","https://openalex.org/W2039948074","https://openalex.org/W2039998381","https://openalex.org/W2079408923","https://openalex.org/W2085876742","https://openalex.org/W2130709397","https://openalex.org/W2162994165","https://openalex.org/W2618478924","https://openalex.org/W2747238620","https://openalex.org/W2899899089","https://openalex.org/W2970641574","https://openalex.org/W3045733287","https://openalex.org/W3082004699","https://openalex.org/W3119928075","https://openalex.org/W4213250451","https://openalex.org/W4312019653","https://openalex.org/W4372285681","https://openalex.org/W4377220931","https://openalex.org/W4385237390","https://openalex.org/W4386347008","https://openalex.org/W4386833333","https://openalex.org/W4401907172","https://openalex.org/W4402666573","https://openalex.org/W4405491756"],"related_works":[],"abstract_inverted_index":{"Transcribing":[0],"naturalistic":[1,73,168],"caregiver-child":[2],"interactions":[3],"is":[4],"a":[5,70,96,150],"labor-intensive":[6],"task":[7],"in":[8,47,113,171],"developmental":[9,172],"research.":[10,173],"While":[11],"automatic":[12],"speech":[13,31,41,117,169],"recognition":[14],"(ASR)":[15],"models":[16],"offer":[17],"potential":[18],"solutions,":[19],"current":[20],"ASR":[21,59,155],"systems,":[22],"including":[23,106],"OpenAI\u2019s":[24],"Whisper,":[25,105],"were":[26],"primarily":[27],"trained":[28],"on":[29,69,141],"adult-directed":[30],"(ADS)":[32],"and":[33,52,92,94,115,118,133,144],"have":[34],"not":[35],"been":[36],"systematically":[37],"evaluated":[38,84],"for":[39,58,153],"infant-directed":[40],"(IDS).":[42],"IDS":[43,138],"differs":[44],"from":[45],"ADS":[46],"prosody,":[48],"phonetics,":[49],"utterance":[50,107],"structure,":[51],"lexical":[53],"patterns,":[54],"posing":[55],"unique":[56],"challenges":[57],"transcription.":[60],"In":[61],"this":[62],"study,":[63],"we":[64,148],"benchmarked":[65],"Whisper\u2019s":[66,85],"transcription":[67,159],"accuracy":[68],"dataset":[71],"of":[72,165],"caregiverinfant":[74],"recordings,":[75],"comparing":[76],"ASR-generated":[77],"transcripts":[78],"to":[79,99,135,161],"human-annotated":[80],"gold-standard":[81],"transcriptions.":[82],"We":[83],"performance":[86],"using":[87],"word":[88,121],"error":[89,111],"rate":[90],"(WER)":[91],"accuracy,":[93],"conducted":[95],"failure":[97],"analysis":[98],"identify":[100],"systematic":[101],"errors":[102],"made":[103],"by":[104],"segmentation":[108],"mismatches,":[109],"high":[110],"rates":[112],"short":[114],"repetitive":[116],"inconsistent":[119],"filler":[120],"handling.":[122],"Results":[123],"indicated":[124],"that":[125],"Whisper":[126],"struggles":[127],"with":[128,157],"short,":[129],"contextually":[130],"ambiguous":[131],"utterances":[132],"fails":[134],"reliably":[136],"segment":[137],"utterances.":[139],"Based":[140],"these":[142],"results":[143],"early":[145],"user":[146],"experience,":[147],"propose":[149],"preliminary":[151],"pipeline":[152],"integrating":[154],"technology":[156],"human":[158],"workflows":[160],"enhance":[162],"the":[163],"efficiency":[164],"processing":[166],"large-scale":[167],"data":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}