{"id":"https://openalex.org/W4392908946","doi":"https://doi.org/10.1109/icassp48485.2024.10447263","title":"USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models","display_name":"USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908946","doi":"https://doi.org/10.1109/icassp48485.2024.10447263"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447263","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5078020198","display_name":"Guanlong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanlong Zhao","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029030495","display_name":"Jason Pelecanos","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Pelecanos","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hank Liao","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103123086","display_name":"Yiling Huang","orcid":"https://orcid.org/0009-0008-0554-0942"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiling Huang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108047863","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-5483-0243"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9164,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77320759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"33","issue":null,"first_page":"11801","last_page":"11805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9426000118255615,"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":0.9426000118255615,"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/computer-science","display_name":"Computer science","score":0.6986076235771179},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6630493998527527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5165149569511414},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.46827197074890137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3962123692035675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3588358759880066},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06561356782913208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986076235771179},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6630493998527527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5165149569511414},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.46827197074890137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3962123692035675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3588358759880066},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06561356782913208},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447263","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2171700247","https://openalex.org/W2589330059","https://openalex.org/W2673722796","https://openalex.org/W2889203268","https://openalex.org/W2936774411","https://openalex.org/W2953212265","https://openalex.org/W3015678936","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3109950060","https://openalex.org/W3147994063","https://openalex.org/W3195577433","https://openalex.org/W3196525293","https://openalex.org/W3197642003","https://openalex.org/W3203417382","https://openalex.org/W4225295099","https://openalex.org/W4286908472","https://openalex.org/W4287113019","https://openalex.org/W4292968575","https://openalex.org/W4307415927","https://openalex.org/W4323066695","https://openalex.org/W4372259861","https://openalex.org/W4372344102","https://openalex.org/W4375868785","https://openalex.org/W4375869109","https://openalex.org/W6603931906","https://openalex.org/W6751104502","https://openalex.org/W6780218876","https://openalex.org/W6797716411","https://openalex.org/W6800751262","https://openalex.org/W6802591457","https://openalex.org/W6810673746","https://openalex.org/W6840509714","https://openalex.org/W6846909052","https://openalex.org/W6847363464","https://openalex.org/W6850218400"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2568858292","https://openalex.org/W1515964938","https://openalex.org/W2389381914","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,55,72,131],"introduce":[1],"a":[2,26,32,46,52,67,90,161],"multilingual":[3,61],"speaker":[4,13,62,84,110],"change":[5,63,85,111],"detection":[6,64,86,112],"model":[7,22,29,50,65,77,105,127,144,150,154],"(USM-SCD)":[8],"that":[9,74,93,134],"can":[10,78,106],"simultaneously":[11],"detect":[12],"turns":[14],"and":[15,37,118],"perform":[16],"ASR":[17,157,164],"for":[18,51],"96":[19,98],"languages.":[20,99],"This":[21],"is":[23],"adapted":[24],"from":[25,45,97],"speech":[27],"foundation":[28,49],"trained":[30],"on":[31],"large":[33,47],"quantity":[34],"of":[35,43,59,69,95,141],"supervised":[36],"unsupervised":[38],"data,":[39],"demonstrating":[40],"the":[41,57,75,103,123,142,148],"utility":[42],"fine-tuning":[44],"generic":[48],"downstream":[53],"task.":[54],"analyze":[56],"performance":[58],"this":[60],"through":[66],"series":[68],"ablation":[70],"studies.":[71],"show":[73,133],"USM-SCD":[76,104,153],"achieve":[79,107,147],"more":[80],"than":[81],"75%":[82],"average":[83],"F1":[87,113],"score":[88,114],"across":[89,115],"test":[91,120],"set":[92],"consists":[94],"data":[96],"On":[100],"American":[101],"English,":[102],"an":[108],"85.8%":[109],"various":[116],"public":[117,163],"internal":[119],"sets,":[121],"beating":[122],"previous":[124],"monolingual":[125],"baseline":[126],"by":[128],"21%":[129],"relative.":[130],"also":[132],"we":[135],"only":[136],"need":[137],"to":[138,146,169],"fine-tune":[139],"one-quarter":[140],"trainable":[143],"parameters":[145],"best":[149],"performance.":[151],"The":[152],"exhibits":[155],"state-of-the-art":[156],"quality":[158],"compared":[159],"with":[160,173],"strong":[162],"baseline,":[165],"making":[166],"it":[167],"suitable":[168],"handle":[170],"both":[171],"tasks":[172],"negligible":[174],"additional":[175],"computational":[176],"cost.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}