{"id":"https://openalex.org/W2890244912","doi":"https://doi.org/10.1109/icassp.2018.8461893","title":"End-to-End Multi-Speaker Speech Recognition","display_name":"End-to-End Multi-Speaker Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890244912","doi":"https://doi.org/10.1109/icassp.2018.8461893","mag":"2890244912"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5007445208","display_name":"Shane Settle","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shane Settle","raw_affiliation_strings":["TTI-Chicago, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TTI-Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"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":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"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":"Takaaki Hori","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":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","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/A5112763337","display_name":"John R. Hershey","orcid":null},"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":"John R. Hershey","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4819","last_page":"4823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8363047242164612},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7628583908081055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6978468298912048},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5266839265823364},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.511907696723938},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4983389377593994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4884859323501587},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47929614782333374},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4665064215660095},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4542827904224396},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44904932379722595},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.4262005388736725},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21969062089920044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11234766244888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363047242164612},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7628583908081055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6978468298912048},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5266839265823364},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.511907696723938},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4983389377593994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4884859323501587},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47929614782333374},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4665064215660095},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4542827904224396},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44904932379722595},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4262005388736725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21969062089920044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11234766244888306},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W2079362249","https://openalex.org/W2127141656","https://openalex.org/W2129116669","https://openalex.org/W2130942839","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2739883972","https://openalex.org/W2891405874","https://openalex.org/W2962715207","https://openalex.org/W2963773971","https://openalex.org/W6623517193","https://openalex.org/W6629014544","https://openalex.org/W6679436768","https://openalex.org/W6679489070","https://openalex.org/W6688843265","https://openalex.org/W6718827390","https://openalex.org/W6728030952","https://openalex.org/W6729728456","https://openalex.org/W6730148858","https://openalex.org/W6741672453","https://openalex.org/W6754999120"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2556771176","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Current":[0],"advances":[1],"in":[2,7,32,102,113],"deep":[3,40,58,145],"learning":[4,146],"have":[5,37],"resulted":[6],"a":[8,13],"convergence":[9],"of":[10,16,24,65,152],"methods":[11,42,55],"across":[12],"wide":[14],"range":[15],"tasks,":[17],"opening":[18],"the":[19,61,89,118,139,162],"door":[20],"for":[21,43,76,91,148],"tighter":[22],"integration":[23],"modules":[25],"that":[26,180],"were":[27],"previously":[28],"developed":[29],"and":[30,47,115,150,164,185,188],"optimized":[31],"isolation.":[33],"Recent":[34],"ground-breaking":[35],"works":[36],"produced":[38],"end-to-end":[39,48],"network":[41],"both":[44],"speech":[45,50,69,83,90,98,154],"separation":[46,54,84,99,149,163],"automatic":[49],"recognition":[51,151,165],"(ASR).":[52],"Speech":[53],"such":[56],"as":[57],"clustering":[59],"address":[60],"challenging":[62],"cocktail-party":[63],"problem":[64],"distinguishing":[66],"multiple":[67],"simultaneous":[68],"signals.":[70,155],"This":[71],"is":[72,122,190],"an":[73,103,170],"enabling":[74],"technology":[75],"real-world":[77],"human":[78],"machine":[79],"interaction":[80],"(HMI).":[81],"However,":[82],"requires":[85,97],"ASR":[86,96],"to":[87,100,124,166,192],"interpret":[88],"any":[92],"HMI":[93],"task.":[94],"Likewise,":[95],"work":[101],"unconstrained":[104],"environment.":[105],"Although":[106],"these":[107],"two":[108],"components":[109],"can":[110],"be":[111,125],"trained":[112,144],"isolation":[114],"connected":[116],"after":[117],"fact,":[119],"this":[120,135],"paradigm":[121],"likely":[123],"sub-optimal,":[126],"since":[127],"it":[128,173],"relies":[129],"on":[130,176,196],"artificially":[131],"mixed":[132,183],"data.":[133,199],"In":[134],"paper,":[136],"we":[137],"develop":[138],"first":[140],"fully":[141],"end-to-end,":[142],"jointly":[143],"system":[147],"overlapping":[153],"The":[156],"joint":[157],"training":[158,175,195],"framework":[159],"synergistically":[160],"adapts":[161],"each":[167],"other.":[168],"As":[169],"additional":[171],"benefit,":[172],"enables":[174],"more":[177],"realistic":[178],"data":[179],"contains":[181],"only":[182],"signals":[184],"their":[186],"transcriptions,":[187],"thus":[189],"suited":[191],"large":[193],"scale":[194],"existing":[197],"transcribed":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}