{"id":"https://openalex.org/W4408353371","doi":"https://doi.org/10.1109/icassp49660.2025.10889307","title":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","display_name":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353371","doi":"https://doi.org/10.1109/icassp49660.2025.10889307"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5030974769","display_name":"Anfeng Xu","orcid":"https://orcid.org/0000-0002-4149-3919"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anfeng Xu","raw_affiliation_strings":["University of Southern California,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567944","display_name":"Tiantian Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049663620","display_name":"Helen Tager\u2010Flusberg","orcid":"https://orcid.org/0000-0002-8768-5414"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helen Tager-Flusberg","raw_affiliation_strings":["Boston University,Boston,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Boston,USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082294410","display_name":"Catherine Lord","orcid":"https://orcid.org/0000-0001-5633-1253"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine Lord","raw_affiliation_strings":["University of California, Los Angeles,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles,Los Angeles,USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01684338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9804999828338623,"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/T12031","display_name":"Speech and dialogue systems","score":0.965499997138977,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8115983009338379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126451730728149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5612897276878357},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40759843587875366}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8115983009338379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126451730728149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5612897276878357},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40759843587875366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317469","display_name":"Apple","ror":"https://ror.org/059hsda18"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W389331340","https://openalex.org/W2135114643","https://openalex.org/W2593116425","https://openalex.org/W2750259098","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W2979826702","https://openalex.org/W3031133340","https://openalex.org/W3084704861","https://openalex.org/W3097945073","https://openalex.org/W3157070662","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3196857193","https://openalex.org/W3209984917","https://openalex.org/W3212886388","https://openalex.org/W4224939064","https://openalex.org/W4229440279","https://openalex.org/W4295455591","https://openalex.org/W4297841362","https://openalex.org/W4385822277","https://openalex.org/W4385822353","https://openalex.org/W4385822468","https://openalex.org/W4385823034","https://openalex.org/W4391733873","https://openalex.org/W4392904074","https://openalex.org/W4402112490","https://openalex.org/W6688816777","https://openalex.org/W6754496211","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Automating":[0],"child":[1],"speech":[2],"analysis":[3],"is":[4,19,53],"crucial":[5],"for":[6,50],"applications":[7],"such":[8],"as":[9],"neurocognitive":[10],"assessments.":[11],"Speaker":[12],"diarization,":[13],"which":[14],"identifies":[15],"\"who":[16],"spoke":[17],"when\",":[18],"an":[20],"essential":[21],"component":[22],"of":[23,43,103],"the":[24,111,119],"automated":[25],"analysis.":[26],"However,":[27],"publicly":[28,129],"available":[29],"child-adult":[30,70,86,120],"speaker":[31,87,121],"diarization":[32,88,122],"solutions":[33],"are":[34,128],"scarce":[35],"due":[36],"to":[37],"privacy":[38],"concerns":[39],"and":[40,56,118],"a":[41,64,77],"lack":[42],"annotated":[44],"datasets,":[45],"while":[46],"manually":[47],"annotating":[48],"data":[49],"each":[51],"scenario":[52],"both":[54],"time-consuming":[55],"costly.":[57],"To":[58],"overcome":[59],"these":[60],"challenges,":[61],"we":[62],"propose":[63],"data-efficient":[65],"solution":[66],"by":[67],"creating":[68],"simulated":[69,126],"conversations":[71,127],"using":[72,89],"AudioSet.":[73],"We":[74],"then":[75],"train":[76,105],"Whisper":[78],"Encoder-based":[79],"model,":[80],"achieving":[81],"strong":[82],"zero-shot":[83],"performance":[84,94],"on":[85,125],"real":[90,104],"datasets.":[91],"The":[92,115],"model":[93,123],"improves":[95],"substantially":[96],"when":[97],"fine-tuned":[98],"with":[99,107],"only":[100],"30":[101],"minutes":[102],"data,":[106],"LoRA":[108],"further":[109],"improving":[110],"transfer":[112],"learning":[113],"performance.":[114],"source":[116],"code":[117],"trained":[124],"available.":[130]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}