{"id":"https://openalex.org/W3015834770","doi":"https://doi.org/10.1109/icassp40776.2020.9054029","title":"End-To-End Multi-Speaker Speech Recognition With Transformer","display_name":"End-To-End Multi-Speaker Speech Recognition With Transformer","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015834770","doi":"https://doi.org/10.1109/icassp40776.2020.9054029","mag":"3015834770"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence & SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence & SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence & SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence & SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6134","last_page":"6138"},"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":0.9983999729156494,"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":0.7758435606956482},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6817420721054077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6732810735702515},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5742359757423401},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5499581098556519},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.48239457607269287},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44661396741867065},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.43134722113609314},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.418447881937027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40817585587501526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37272727489471436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16914382576942444},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12019333243370056},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07740193605422974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758435606956482},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6817420721054077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6732810735702515},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5742359757423401},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5499581098556519},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.48239457607269287},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44661396741867065},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.43134722113609314},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.418447881937027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40817585587501526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37272727489471436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16914382576942444},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12019333243370056},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07740193605422974},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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:10.1109/icassp40776.2020.9054029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1983812858","https://openalex.org/W1991139021","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2600628583","https://openalex.org/W2750380122","https://openalex.org/W2802023636","https://openalex.org/W2886180730","https://openalex.org/W2889144942","https://openalex.org/W2889503488","https://openalex.org/W2890244912","https://openalex.org/W2892163332","https://openalex.org/W2896457183","https://openalex.org/W2943934118","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2963197115","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3008357631","https://openalex.org/W3008762051","https://openalex.org/W4385245566","https://openalex.org/W6688843265","https://openalex.org/W6735168207","https://openalex.org/W6736173540","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880"],"abstract_inverted_index":{"Recently,":[0],"fully":[1],"recurrent":[2],"neural":[3,72],"network":[4,69],"(RNN)":[5],"based":[6],"end-to-end":[7],"models":[8,35,133],"have":[9],"been":[10],"proven":[11],"to":[12,62,83,86,96,119,142,172],"be":[13,84],"effective":[14],"for":[15,36],"multi-speaker":[16],"speech":[17,52],"recognition":[18,53],"in":[19,50,60,66,74,94,151,158],"both":[20],"the":[21,31,47,51,64,67,71,75,80,91,100,111,125,131,148,159],"single-channel":[22,152],"and":[23,136,144,153,166,174],"multi-channel":[24,76,154],"scenarios.":[25],"In":[26],"this":[27],"work,":[28],"we":[29,45,78,104],"explore":[30],"use":[32,63],"of":[33,70],"Transformer":[34,57,65],"these":[37],"tasks":[38],"by":[39],"focusing":[40],"on":[41,124],"two":[42],"aspects.":[43],"First,":[44],"replace":[46],"RNN-based":[48],"encoder-decoder":[49],"model":[54,101,118],"with":[55],"a":[56,87],"architecture.":[58],"Second,":[59],"order":[61,95],"masking":[68],"beamformer":[73],"case,":[77,161],"modify":[79],"self-attention":[81],"component":[82],"restricted":[85],"segment":[88],"rather":[89],"than":[90],"whole":[92],"sequence":[93],"reduce":[97],"computation.":[98],"Besides":[99],"architecture":[102],"improvements,":[103],"also":[105],"incorporate":[106],"an":[107],"external":[108],"dereverberation":[109],"preprocessing,":[110],"weighted":[112],"prediction":[113],"error":[114],"(WPE),":[115],"enabling":[116],"our":[117,162],"handle":[120],"reverberated":[121],"signals.":[122],"Experiments":[123],"spatialized":[126],"wsj1-2mix":[127],"corpus":[128],"show":[129],"that":[130],"Transformer-based":[132],"achieve":[134,164],"40.9%":[135],"25.6%":[137],"relative":[138,168],"WER":[139,169],"reduction,":[140,170],"down":[141,171],"12.1%":[143],"6.4%":[145],"WER,":[146],"under":[147],"anechoic":[149],"condition":[150],"tasks,":[155],"respectively,":[156],"while":[157],"reverberant":[160],"methods":[163],"41.5%":[165],"13.8%":[167],"16.5%":[173],"15.2%":[175],"WER.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}