{"id":"https://openalex.org/W3196194966","doi":"https://doi.org/10.21437/interspeech.2021-101","title":"End-to-End Speaker-Attributed ASR with Transformer","display_name":"End-to-End Speaker-Attributed ASR with Transformer","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196194966","doi":"https://doi.org/10.21437/interspeech.2021-101","mag":"3196194966"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-101","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":false,"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/A5008578397","display_name":"Guoli Ye","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":"Guoli Ye","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/A5046637354","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0001-5490-5591"},"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/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/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":true,"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/A5101618071"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.1122,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.89431361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4413","last_page":"4417"},"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":0.9998000264167786,"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":0.9993000030517578,"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":0.8245905637741089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7590569257736206},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7196930646896362},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6603704690933228},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5742807388305664},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5405953526496887},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47989022731781006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3932955861091614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3804277777671814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245905637741089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7590569257736206},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7196930646896362},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6603704690933228},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5742807388305664},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5405953526496887},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47989022731781006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3932955861091614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3804277777671814},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-101","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1876378865","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2939690918","https://openalex.org/W2952752702","https://openalex.org/W2963477857","https://openalex.org/W2963773971","https://openalex.org/W2963979492","https://openalex.org/W2972818416","https://openalex.org/W2973127116","https://openalex.org/W2973730722","https://openalex.org/W2999547272","https://openalex.org/W3000358149","https://openalex.org/W3008191852","https://openalex.org/W3008283340","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3094831814","https://openalex.org/W3095822285","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3105031100","https://openalex.org/W3109079702","https://openalex.org/W3143843080","https://openalex.org/W3154262773","https://openalex.org/W3160133086","https://openalex.org/W3162847598","https://openalex.org/W4288083483","https://openalex.org/W4309845474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2499802997","https://openalex.org/W4255044973","https://openalex.org/W3037446006","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2464377622","https://openalex.org/W2914064142","https://openalex.org/W2394963835"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"recent":[4],"effort":[5],"on":[6,37,66],"end-to-end":[7],"speakerattributed":[8,89],"automatic":[9],"speech":[10,17],"recognition,":[11],"which":[12,103,133],"jointly":[13],"performs":[14],"speaker":[15,20,53,58,128],"counting,":[16],"recognition":[18],"and":[19,82,122,125],"identification":[21,59],"for":[22,99,138],"monaural":[23,142],"multi-talker":[24],"audio.Firstly,":[25],"we":[26,50],"thoroughly":[27],"update":[28],"the":[29,67,72,80,84,88,96,100,111,135,141],"model":[30,86,113],"architecture":[31,74],"that":[32,71,83],"was":[33],"previously":[34],"designed":[35],"based":[36],"a":[38,52],"long":[39],"short-term":[40],"memory":[41],"(LSTM)-based":[42],"attention":[43],"encoder":[44],"decoder":[45],"by":[46,93],"applying":[47],"transformer":[48],"architectures.Secondly,":[49],"propose":[51],"deduplication":[54],"mechanism":[55],"to":[56],"reduce":[57],"errors":[60],"in":[61],"highly":[62],"overlapped":[63,109],"regions.Experimental":[64],"results":[65,137],"LibriSpeechMix":[68],"dataset":[69],"shows":[70],"transformer-based":[73],"is":[75],"especially":[76],"good":[77],"at":[78],"counting":[79],"speakers":[81],"proposed":[85,112],"reduces":[87],"word":[90,117],"error":[91,118],"rate":[92],"47%":[94],"over":[95],"LSTM-based":[97],"baseline.Furthermore,":[98],"LibriCSS":[101,139],"dataset,":[102],"consists":[104],"of":[105,108,120,132],"real":[106],"recordings":[107],"speech,":[110],"achieves":[114],"concatenated":[115],"minimum-permutation":[116],"rates":[119],"11.9%":[121],"16.3%":[123],"with":[124,140],"without":[126],"target":[127],"profiles,":[129],"respectively,":[130],"both":[131],"are":[134],"state-of-the-art":[136],"setting.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}