{"id":"https://openalex.org/W4375869109","doi":"https://doi.org/10.1109/icassp49357.2023.10096361","title":"Speaker Change Detection For Transformer Transducer ASR","display_name":"Speaker Change Detection For Transformer Transducer ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869109","doi":"https://doi.org/10.1109/icassp49357.2023.10096361"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051153953","display_name":"Min Hu","orcid":"https://orcid.org/0000-0002-2974-1107"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Hu","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365056","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-5206-8600"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101674460"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.6952,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74748033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"30","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7946622371673584},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6664975881576538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6463071703910828},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4242584705352783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.40513497591018677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37101465463638306},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10321229696273804},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09168565273284912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946622371673584},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6664975881576538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6463071703910828},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4242584705352783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40513497591018677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37101465463638306},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10321229696273804},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09168565273284912},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2081074144","https://openalex.org/W2673722796","https://openalex.org/W2746241180","https://openalex.org/W2936794852","https://openalex.org/W2962760690","https://openalex.org/W2963015630","https://openalex.org/W2963227667","https://openalex.org/W2963351448","https://openalex.org/W2970568180","https://openalex.org/W2973127116","https://openalex.org/W3015927303","https://openalex.org/W3016232124","https://openalex.org/W3024400986","https://openalex.org/W3095311338","https://openalex.org/W3095822285","https://openalex.org/W3133848124","https://openalex.org/W3161873870","https://openalex.org/W3163907627","https://openalex.org/W3203417382","https://openalex.org/W3209984917","https://openalex.org/W3211278025","https://openalex.org/W3212886388","https://openalex.org/W4210811812","https://openalex.org/W4226491018","https://openalex.org/W4297841653","https://openalex.org/W4297841778","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6777196455","https://openalex.org/W6842451222"],"related_works":["https://openalex.org/W3015678144","https://openalex.org/W2798423868","https://openalex.org/W3027026357","https://openalex.org/W2962906565","https://openalex.org/W142195158","https://openalex.org/W3033772826","https://openalex.org/W752237738","https://openalex.org/W2913095682","https://openalex.org/W1559469979","https://openalex.org/W3154635860"],"abstract_inverted_index":{"Speaker":[0],"change":[1,32,112],"detection":[2],"(SCD)":[3],"is":[4,85],"an":[5,17,81,90],"important":[6],"feature":[7],"that":[8,108,134],"improves":[9],"the":[10,13,25,42,60,77,100,119,129,140],"readability":[11],"of":[12,89,99],"recognized":[14,47],"words":[15],"from":[16],"automatic":[18],"speech":[19],"recognition":[20],"(ASR)":[21],"system":[22],"by":[23],"breaking":[24],"word":[26,48],"sequence":[27],"into":[28],"paragraphs":[29],"at":[30],"speaker":[31,111],"points.":[33],"Existing":[34],"SCD":[35,78,83,101,122,158],"solutions":[36],"either":[37],"require":[38],"additional":[39,82],"ensemble":[40],"for":[41,64,76,114,128],"time":[43],"based":[44],"decisions":[45],"and":[46,57,121,145,159],"sequences,":[49],"or":[50],"implement":[51],"a":[52,73,156],"tight":[53],"integration":[54],"between":[55],"ASR":[56,94,120,152,160],"SCD,":[58],"limiting":[59],"potential":[61],"optimum":[62],"performance":[63],"both":[65],"tasks.":[66],"To":[67],"address":[68],"these":[69],"issues,":[70],"we":[71],"propose":[72],"novel":[74],"framework":[75,107],"task,":[79],"where":[80],"module":[84],"built":[86],"on":[87,143],"top":[88],"existing":[91],"Transformer":[92],"Transducer":[93],"(TT-ASR)":[95],"network.":[96],"Two":[97],"variants":[98],"network":[102],"are":[103],"explored":[104],"in":[105],"this":[106],"naturally":[109],"estimate":[110],"probability":[113],"each":[115],"word,":[116],"while":[117],"allowing":[118],"to":[123],"have":[124],"independent":[125],"optimization":[126],"scheme":[127],"best":[130],"performance.":[131],"Experiments":[132],"show":[133],"our":[135],"methods":[136],"can":[137],"significantly":[138],"improve":[139],"F1":[141],"score":[142],"LibriCSS":[144],"Microsoft":[146],"call":[147],"center":[148],"data":[149],"sets":[150],"without":[151],"degradation,":[153],"compared":[154],"with":[155],"joint":[157],"baseline.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}