{"id":"https://openalex.org/W3160133086","doi":"https://doi.org/10.1109/icassp39728.2021.9415062","title":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","display_name":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160133086","doi":"https://doi.org/10.1109/icassp39728.2021.9415062","mag":"3160133086"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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 Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, 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 Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"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":"Liang Lu","raw_affiliation_strings":["Microsoft Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, 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 Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, 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 Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, 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 Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, 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 Corp, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, 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":1.9036,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88114683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6503","last_page":"6507"},"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":0.9994999766349792,"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":0.9961000084877014,"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/speech-recognition","display_name":"Speech recognition","score":0.790468692779541},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.681481122970581},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6668142080307007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6616946458816528},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6215841770172119},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5777217745780945},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.45759162306785583},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4552156329154968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4065853953361511},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3823065161705017},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08663243055343628}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.790468692779541},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.681481122970581},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6668142080307007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6616946458816528},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6215841770172119},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5777217745780945},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.45759162306785583},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4552156329154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065853953361511},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3823065161705017},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08663243055343628},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1591607137","https://openalex.org/W1828163288","https://openalex.org/W1876378865","https://openalex.org/W1987238397","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2131342762","https://openalex.org/W2221409856","https://openalex.org/W2291513470","https://openalex.org/W2460742184","https://openalex.org/W2569324142","https://openalex.org/W2653985929","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2888909726","https://openalex.org/W2889163603","https://openalex.org/W2939690918","https://openalex.org/W2952752702","https://openalex.org/W2963477857","https://openalex.org/W2963747784","https://openalex.org/W2963773971","https://openalex.org/W2963979492","https://openalex.org/W2973127116","https://openalex.org/W2990501692","https://openalex.org/W2999547272","https://openalex.org/W3000358149","https://openalex.org/W3007946293","https://openalex.org/W3008283340","https://openalex.org/W3025834604","https://openalex.org/W3094821064","https://openalex.org/W3094979069","https://openalex.org/W3095697114","https://openalex.org/W3095822285","https://openalex.org/W3097643313","https://openalex.org/W3143843080","https://openalex.org/W3154262773","https://openalex.org/W6623517193","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6639431793","https://openalex.org/W6662018943","https://openalex.org/W6678809451","https://openalex.org/W6770425081","https://openalex.org/W6771611251","https://openalex.org/W6780226713","https://openalex.org/W6782161367"],"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":{"Recently,":[0],"an":[1],"end-to-end":[2],"speaker-attributed":[3,40,91,102],"automatic":[4],"speech":[5,19,71],"recognition":[6,20],"(E2E":[7],"SA-ASR)":[8],"model":[9,15,33],"was":[10,81],"proposed":[11,132],"as":[12],"a":[13,101],"joint":[14,49],"of":[16,73,76],"speaker":[17,22,56],"counting,":[18],"and":[21,55],"identification":[23,57],"for":[24,52,69],"monaural":[25],"overlapped":[26,70],"speech.":[27],"In":[28,96],"the":[29,32,39,48,78,86,110,117,121,126,131,136,144],"previous":[30],"study,":[31],"parameters":[34,111],"were":[35],"trained":[36,113],"based":[37],"on":[38],"maximum":[41],"mutual":[42],"information":[43],"(SA-MMI)":[44],"criterion,":[45],"with":[46,143],"which":[47],"posterior":[50],"probability":[51],"multi-talker":[53],"transcription":[54],"are":[58,112],"maximized":[59],"over":[60,120],"training":[61,65,79,107,122,134],"data.":[62,123],"Although":[63],"SA-MMI":[64],"showed":[66],"promising":[67],"results":[68],"consisting":[72],"various":[74],"numbers":[75],"speakers,":[77],"criterion":[80],"not":[82],"directly":[83,115],"linked":[84],"to":[85,114],"final":[87],"evaluation":[88],"metric,":[89],"i.e.,":[90],"word":[92],"error":[93],"rate":[94],"(SA-WER).":[95],"this":[97],"paper,":[98],"we":[99],"propose":[100],"minimum":[103],"Bayes":[104],"risk":[105],"(SA-MBR)":[106],"method":[108],"where":[109],"minimize":[116],"expected":[118],"SA-WER":[119,137],"Experiments":[124],"using":[125],"LibriSpeech":[127],"corpus":[128],"show":[129],"that":[130],"SA-MBR":[133],"reduces":[135],"by":[138],"9.0":[139],"%":[140],"relative":[141],"compared":[142],"SA-MMI-trained":[145],"model.":[146],"<sup":[147],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[149]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}