{"id":"https://openalex.org/W3204618061","doi":"https://doi.org/10.1109/icassp43922.2022.9746225","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers Using End-to-End Speaker-Attributed ASR","display_name":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers Using End-to-End Speaker-Attributed ASR","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3204618061","doi":"https://doi.org/10.1109/icassp43922.2022.9746225","mag":"3204618061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746225","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, 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,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"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":"Yashesh Gaur","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363489","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0009-0004-6683-3969"},"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":"Xiaofei Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"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":"Zhong Meng","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, 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,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5016279564"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.2222,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93298858,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8082","last_page":"8086"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9446041584014893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7913886308670044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7667791843414307},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6752045154571533},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5092905759811401},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43685078620910645},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.4303871989250183},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4273383617401123},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3639490604400635},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06143277883529663}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9446041584014893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7913886308670044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667791843414307},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6752045154571533},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5092905759811401},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43685078620910645},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.4303871989250183},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4273383617401123},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3639490604400635},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06143277883529663},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746225","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1556857061","https://openalex.org/W1975884129","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2177420620","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2747874407","https://openalex.org/W2805869973","https://openalex.org/W2808631503","https://openalex.org/W2902864383","https://openalex.org/W2928165649","https://openalex.org/W2963403868","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W2997419692","https://openalex.org/W3008357631","https://openalex.org/W3015780472","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3094122712","https://openalex.org/W3094821064","https://openalex.org/W3094831814","https://openalex.org/W3095212884","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3105031100","https://openalex.org/W3108962419","https://openalex.org/W3125596972","https://openalex.org/W3143843080","https://openalex.org/W3162347631","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3181056718","https://openalex.org/W3196194966","https://openalex.org/W3196595845","https://openalex.org/W3198858272","https://openalex.org/W3203417382","https://openalex.org/W3212886388","https://openalex.org/W4226305408","https://openalex.org/W4285719527","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6633097512","https://openalex.org/W6662018943","https://openalex.org/W6678809451","https://openalex.org/W6739901393","https://openalex.org/W6761176859","https://openalex.org/W6775489429","https://openalex.org/W6775537894","https://openalex.org/W6786127183","https://openalex.org/W6790122275","https://openalex.org/W6801496586","https://openalex.org/W6802013660"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Transcribe-to-Diarize,":[3],"a":[4,25,87,175],"new":[5],"approach":[6],"for":[7,32,132],"neural":[8],"speaker":[9,33,39,115,133,163],"diarization":[10,101,157,164],"that":[11,28,44,62,150],"uses":[12],"an":[13],"end-to-end":[14],"(E2E)":[15],"speaker-attributed":[16,139,194],"automatic":[17],"speech":[18,36,111],"recognition":[19],"(SA-ASR).":[20],"The":[21,189],"E2E":[22,50,83,104],"SA-ASR":[23,51,84,105],"is":[24,107,171,185],"joint":[26],"model":[27,52,106],"was":[29],"recently":[30],"proposed":[31,152,190],"counting,":[34],"multi-talker":[35],"recognition,":[37],"and":[38,65,135,146,173],"identification":[40],"from":[41,77],"monaural":[42],"audio":[43],"contains":[45],"overlapping":[46],"speech.":[47],"Although":[48],"the":[49,63,78,82,95,103,119,144,151,167,181],"originally":[53],"does":[54],"not":[55],"estimate":[56,110],"any":[57],"time-related":[58],"information,":[59],"we":[60],"show":[61,149],"start":[64],"end":[66],"times":[67],"of":[68,81,90,113,121,126,169,183],"each":[69,114],"word":[70],"can":[71],"be":[72],"estimated":[73],"with":[74,196],"sufficient":[75],"accuracy":[76],"internal":[79],"state":[80],"by":[85],"adding":[86],"small":[88],"number":[89,125,168,182],"learnable":[91],"parameters.":[92],"Similar":[93],"to":[94,109,178],"target-speaker":[96],"voice":[97],"activity":[98,112],"detection":[99],"(TS-VAD)-based":[100],"method,":[102],"applied":[108],"while":[116],"it":[117],"has":[118],"advantages":[120],"(i)":[122],"handling":[123],"unlimited":[124],"speakers,":[127],"(ii)":[128],"leveraging":[129],"linguistic":[130],"information":[131],"diarization,":[134],"(iii)":[136],"simultaneously":[137,192],"generating":[138],"transcriptions.":[140],"Experimental":[141],"results":[142],"on":[143],"LibriCSS":[145],"AMI":[147],"corpora":[148],"method":[153,191],"achieves":[154,174],"significantly":[155],"better":[156],"error":[158],"rate":[159],"than":[160],"various":[161],"existing":[162],"methods":[165],"when":[166,180],"speakers":[170,184],"unknown,":[172],"comparable":[176],"performance":[177],"TS-VAD":[179],"given":[186],"in":[187],"advance.":[188],"generates":[193],"transcription":[195],"state-of-the-art":[197],"accuracy.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-03T23:48:18.283914","created_date":"2025-10-10T00:00:00"}