{"id":"https://openalex.org/W3013139777","doi":"https://doi.org/10.21437/interspeech.2020-999","title":"Serialized Output Training for End-to-End Overlapped Speech Recognition","display_name":"Serialized Output Training for End-to-End Overlapped Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3013139777","doi":"https://doi.org/10.21437/interspeech.2020-999","mag":"3013139777"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-999","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016279564"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":4.139,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.94921192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2797","last_page":"2801"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8853165507316589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6862565279006958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6633945107460022},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6393240690231323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3159705400466919}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8853165507316589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6862565279006958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6633945107460022},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6393240690231323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3159705400466919},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-999","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W2144763279","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2222512263","https://openalex.org/W2327501763","https://openalex.org/W2394932179","https://openalex.org/W2407080277","https://openalex.org/W2460742184","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2533523411","https://openalex.org/W2786835190","https://openalex.org/W2888909726","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2963266252","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963979492","https://openalex.org/W2964308564","https://openalex.org/W2973127116","https://openalex.org/W2977728428","https://openalex.org/W2992632249","https://openalex.org/W3008191852","https://openalex.org/W3008480565","https://openalex.org/W3008762051","https://openalex.org/W3015746570","https://openalex.org/W3103005696"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2810751659","https://openalex.org/W258997015"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"serialized":[3],"output":[4,25,41],"training":[5,32,119],"(SOT),":[6],"a":[7,36,98],"novel":[8],"framework":[9],"for":[10,92],"multi-speaker":[11],"overlapped":[12,65,143],"speech":[13,144],"recognition":[14],"based":[15],"on":[16,133],"an":[17,84],"attention-based":[18],"encoder-decoder":[19],"approach.":[20],"Instead":[21],"of":[22,47,60,80,114,126,148,167],"having":[23],"multiple":[24,48,62],"layers":[26],"as":[27],"with":[28,38,145],"the":[29,45,77,88,112,115,118,123,127,138,159,165,170],"permutation":[30],"invariant":[31],"(PIT),":[33],"SOT":[34,67,103,139,160],"uses":[35],"model":[37,87],"only":[39],"one":[40,50],"layer":[42],"that":[43,101,137,158],"generates":[44],"transcriptions":[46,63],"speakers":[49,116,149,168],"after":[51],"another.":[52],"The":[53],"attention":[54],"and":[55,82],"decoder":[56],"modules":[57],"take":[58],"care":[59],"producing":[61],"from":[64],"speech.":[66],"has":[68],"two":[69],"advantages":[70],"over":[71],"PIT:":[72],"(1)":[73],"no":[74],"limitation":[75],"in":[76,107,117,169],"maximum":[78],"number":[79,113,166],"speakers,":[81],"(2)":[83],"ability":[85],"to":[86,104],"dependencies":[89],"among":[90],"outputs":[91],"different":[93],"speakers.":[94],"We":[95,155],"also":[96,156],"propose":[97],"simple":[99],"trick":[100],"allows":[102],"be":[105],"executed":[106],"$O(S)$,":[108],"where":[109],"$S$":[110],"is":[111],"sample,":[120],"by":[121],"using":[122],"start":[124],"times":[125],"constituent":[128],"source":[129],"utterances.":[130],"Experimental":[131],"results":[132],"LibriSpeech":[134],"corpus":[135],"show":[136,157],"models":[140,161],"can":[141,162],"transcribe":[142],"variable":[146],"numbers":[147],"significantly":[150],"better":[151],"than":[152],"PIT-based":[153],"models.":[154],"accurately":[163],"count":[164],"input":[171],"audio.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}