{"id":"https://openalex.org/W3017474798","doi":"https://doi.org/10.1109/taslp.2020.2988423","title":"Improving End-to-End Single-Channel Multi-Talker Speech Recognition","display_name":"Improving End-to-End Single-Channel Multi-Talker Speech Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3017474798","doi":"https://doi.org/10.1109/taslp.2020.2988423","mag":"3017474798"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2988423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2988423","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4500-3515","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-5221-5412","affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.129,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.93126781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"1385","last_page":"1394"},"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":0.9997000098228455,"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":0.9980000257492065,"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":0.8004209995269775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7087993025779724},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6001412272453308},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5776026248931885},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48942938446998596},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42196279764175415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34343186020851135},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24587461352348328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004209995269775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7087993025779724},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6001412272453308},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5776026248931885},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48942938446998596},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42196279764175415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34343186020851135},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24587461352348328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2988423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2988423","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G257170","display_name":null,"funder_award_id":"U1736202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W648786980","https://openalex.org/W1524333225","https://openalex.org/W1569447338","https://openalex.org/W1586532344","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1991139021","https://openalex.org/W2000062601","https://openalex.org/W2016557737","https://openalex.org/W2047527596","https://openalex.org/W2102113734","https://openalex.org/W2112739286","https://openalex.org/W2134797427","https://openalex.org/W2160815625","https://openalex.org/W2176263492","https://openalex.org/W2184045248","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2293634267","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2397970420","https://openalex.org/W2402040300","https://openalex.org/W2460742184","https://openalex.org/W2526425061","https://openalex.org/W2558649592","https://openalex.org/W2568308529","https://openalex.org/W2570666999","https://openalex.org/W2610674366","https://openalex.org/W2734774145","https://openalex.org/W2738829388","https://openalex.org/W2739883972","https://openalex.org/W2766219058","https://openalex.org/W2783538964","https://openalex.org/W2794289187","https://openalex.org/W2889129739","https://openalex.org/W2889144942","https://openalex.org/W2890244912","https://openalex.org/W2892025684","https://openalex.org/W2916979304","https://openalex.org/W2943934118","https://openalex.org/W2962715207","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2962835968","https://openalex.org/W2963211739","https://openalex.org/W2963248296","https://openalex.org/W2963301902","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963620441","https://openalex.org/W2963736842","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W2973091309","https://openalex.org/W3016232124","https://openalex.org/W3099832538","https://openalex.org/W6600284362","https://openalex.org/W6621543089","https://openalex.org/W6631362777","https://openalex.org/W6633847657","https://openalex.org/W6635078382","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6675365184","https://openalex.org/W6679909955","https://openalex.org/W6685322675","https://openalex.org/W6687566353","https://openalex.org/W6696934422","https://openalex.org/W6712413127","https://openalex.org/W6712847557","https://openalex.org/W6748559479"],"related_works":["https://openalex.org/W2401567014","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Although":[0],"significant":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"in":[6,141,192],"single-talker":[7,22,47],"automatic":[8],"speech":[9,23,159,180],"recognition":[10,24],"(ASR),":[11],"there":[12],"is":[13,50],"still":[14],"a":[15,53],"large":[16],"performance":[17,190],"gap":[18],"between":[19],"multi-talker":[20,35,54,145,178,208],"and":[21,38,78,106,113,153,198],"systems.":[25],"In":[26],"this":[27],"article,":[28],"we":[29],"propose":[30],"an":[31,132],"enhanced":[32],"end-to-end":[33,48,144,207],"monaural":[34],"ASR":[36,146,209],"architecture":[37,55],"training":[39,59],"strategy":[40],"to":[41,52,65,118,136,204],"recognize":[42],"the":[43,67,83,88,104,110,120,125,129,137,142,156,163,177,205],"overlapped":[44],"speech.":[45],"The":[46,167,182],"model":[49,121,135,140],"extended":[51],"with":[56],"permutation":[57],"invariant":[58],"(PIT).":[60],"Several":[61],"methods":[62],"are":[63,116,151],"designed":[64],"enhance":[66,103],"system":[68,184],"performance,":[69],"including":[70],"speaker":[71,84],"parallel":[72,85],"attention,":[73],"scheduled":[74,111],"sampling,":[75],"curriculum":[76,114],"learning":[77,115],"knowledge":[79,126,130],"distillation.":[80],"More":[81],"specifically,":[82],"attention":[86,92,96],"extends":[87],"basic":[89,206],"single":[90],"shared":[91],"module":[93],"into":[94],"multiple":[95],"modules":[97],"for":[98],"each":[99],"speaker,":[100],"which":[101],"can":[102,174],"tracing":[105],"separation":[107],"ability.":[108],"Then":[109],"sampling":[112],"proposed":[117,143,149,172],"make":[119],"better":[122],"optimized.":[123],"Finally":[124],"distillation":[127],"transfers":[128],"from":[131,162],"original":[133],"single-speaker":[134],"current":[138],"multi-speaker":[139],"structure.":[147],"Our":[148],"architectures":[150,173],"evaluated":[152],"compared":[154,203],"on":[155],"artificially":[157],"mixed":[158,179],"datasets":[160],"generated":[161],"WSJ0":[164],"reading":[165],"corpus.":[166],"experiments":[168],"demonstrate":[169],"that":[170],"our":[171],"significantly":[175],"improve":[176],"recognition.":[181],"final":[183],"obtains":[185],"more":[186],"than":[187],"15%":[188],"relative":[189],"gains":[191],"both":[193],"character":[194],"error":[195,200],"rate":[196,201],"(CER)":[197],"word":[199],"(WER)":[202],"system.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}