{"id":"https://openalex.org/W3181056718","doi":"https://doi.org/10.21437/interspeech.2021-102","title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","display_name":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3181056718","doi":"https://doi.org/10.21437/interspeech.2021-102","mag":"3181056718"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-102","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-102","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/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"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":"Yu Wu","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/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"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":8,"corresponding_author_ids":["https://openalex.org/A5101618071"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.7999,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9202665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3430","last_page":"3434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.7950491309165955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7470977306365967},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6899508237838745},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5855624675750732},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5447521805763245},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5108253955841064},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5055038928985596},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4969034492969513},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4825565218925476},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4820040762424469},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44932490587234497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34882599115371704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950491309165955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7470977306365967},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6899508237838745},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5855624675750732},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5447521805763245},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5108253955841064},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5055038928985596},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4969034492969513},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4825565218925476},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4820040762424469},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44932490587234497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34882599115371704},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-102","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-102","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1876378865","https://openalex.org/W2081074144","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2159591770","https://openalex.org/W2294108103","https://openalex.org/W2407080277","https://openalex.org/W2460742184","https://openalex.org/W2696967604","https://openalex.org/W2729190387","https://openalex.org/W2796868621","https://openalex.org/W2936774411","https://openalex.org/W2939690918","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963979492","https://openalex.org/W2973049979","https://openalex.org/W3008283340","https://openalex.org/W3015746570","https://openalex.org/W3015834770","https://openalex.org/W3016232124","https://openalex.org/W3017474798","https://openalex.org/W3020336359","https://openalex.org/W3036601975","https://openalex.org/W3094831814","https://openalex.org/W3095184753","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3109079702","https://openalex.org/W3139918052","https://openalex.org/W3143843080","https://openalex.org/W3162354890","https://openalex.org/W3162847598","https://openalex.org/W3212886388","https://openalex.org/W4288083483","https://openalex.org/W4309845474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W3096273170","https://openalex.org/W3045896262"],"abstract_inverted_index":{"Transcribing":[0],"meetings":[1],"containing":[2],"overlapped":[3,36],"speech":[4,22,37],"with":[5,79,162],"only":[6,152],"a":[7,55,62,80,102,129,171,174],"single":[8],"distant":[9],"microphone":[10],"(SDM)":[11],"has":[12],"been":[13,28],"one":[14],"of":[15,83,95,104,107,119,134,160],"the":[16,34,77,116,120,137,156],"most":[17],"challenging":[18],"problems":[19],"for":[20,111,136],"automatic":[21],"recognition":[23,38],"(ASR).While":[24],"various":[25],"approaches":[26],"have":[27],"proposed,":[29],"all":[30],"previous":[31,157],"studies":[32],"on":[33,42,115],"monaural":[35],"problem":[39],"were":[40],"based":[41],"either":[43],"simulation":[44,72],"data":[45,73],"or":[46],"small-scale":[47],"real":[48,84],"data.In":[49],"this":[50],"paper,":[51],"we":[52,59],"extensively":[53],"investigate":[54],"two-step":[56],"approach":[57],"where":[58],"first":[60],"pre-train":[61],"serialized":[63],"output":[64],"training":[65,122],"(SOT)-based":[66],"multi-talker":[67,108],"ASR":[68,126,178],"by":[69,89,173],"using":[70],"large-scale":[71],"and":[74],"then":[75],"fine-tune":[76],"model":[78,127,179],"small":[81],"amount":[82],"meeting":[85],"data.Experiments":[86],"are":[87],"conducted":[88],"utilizing":[90],"75":[91],"thousand":[92],"(K)":[93],"hours":[94,106,118],"our":[96,124],"internal":[97],"single-talker":[98,177],"recording":[99],"to":[100,181],"simulate":[101],"total":[103],"900K":[105],"audio":[109],"segments":[110],"supervised":[112],"pretraining.With":[113],"fine-tuning":[114],"70":[117],"AMI-SDM":[121,138],"data,":[123],"SOT":[125],"achieves":[128],"word":[130],"error":[131],"rate":[132],"(WER)":[133],"21.2%":[135],"evaluation":[139],"set":[140],"while":[141],"automatically":[142],"counting":[143],"speakers":[144],"in":[145],"each":[146],"test":[147],"segment.This":[148],"result":[149,172],"is":[150],"not":[151],"significantly":[153],"better":[154,169],"than":[155,170],"state-of-the-art":[158],"WER":[159],"36.4%":[161],"oracle":[163],"utterance":[164],"boundary":[165],"information":[166],"but":[167],"also":[168],"similarly":[175],"fine-tuned":[176],"applied":[180],"beamformed":[182],"audio.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}