{"id":"https://openalex.org/W3015746570","doi":"https://doi.org/10.1109/icassp40776.2020.9054328","title":"End-To-End Multi-Talker Overlapping Speech Recognition","display_name":"End-To-End Multi-Talker Overlapping Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015746570","doi":"https://doi.org/10.1109/icassp40776.2020.9054328","mag":"3015746570"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054328","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":"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/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anshuman Tripathi","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasim Sak","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101403998"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.7377,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95818656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6129","last_page":"6133"},"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":0.9995999932289124,"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":0.8261914849281311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8115140199661255},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6076436042785645},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.525775671005249},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5113884806632996},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5047711133956909},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4800192415714264},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47639575600624084},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44539880752563477},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3950042724609375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38570407032966614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3762640953063965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261914849281311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8115140199661255},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6076436042785645},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.525775671005249},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5113884806632996},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5047711133956909},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4800192415714264},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47639575600624084},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44539880752563477},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3950042724609375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38570407032966614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3762640953063965},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054328","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":0.6299999952316284,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2221409856","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2604869594","https://openalex.org/W2749660340","https://openalex.org/W2890244912","https://openalex.org/W2962715207","https://openalex.org/W2963122170","https://openalex.org/W2963477857","https://openalex.org/W2963843276","https://openalex.org/W2968418516","https://openalex.org/W2972362771","https://openalex.org/W2973062255","https://openalex.org/W6638749077","https://openalex.org/W6688843265","https://openalex.org/W6718827390","https://openalex.org/W6741874079","https://openalex.org/W6753435171"],"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/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"an":[5],"end-to-end":[6],"speech":[7,14,111,124,145],"recognition":[8],"system":[9],"that":[10,93,142],"can":[11,18,105,114,152],"recognize":[12],"single-channel":[13],"where":[15],"multiple":[16,58],"talkers":[17],"speak":[19],"at":[20],"the":[21,42,100,137],"same":[22,138],"time":[23],"(overlapping":[24],"speech)":[25],"by":[26,46,94],"using":[27,95],"a":[28,48,69,83,116,154],"neural":[29],"network":[30],"model":[31,50,104],"based":[32],"on":[33,120,136],"Recurrent":[34],"Neural":[35],"Network":[36],"Transducer":[37],"(RNN-T)":[38],"architecture.":[39],"We":[40,67,91],"augment":[41],"conventional":[43],"RNN-T":[44,103],"architecture":[45],"including":[47],"masking":[49,70],"for":[51,149],"separation":[52],"of":[53,118,132,156],"encoded":[54],"audio":[55],"features,":[56],"and":[57,82,113],"label":[59],"encoders":[60],"to":[61,73,76,78,87,159],"encode":[62],"transcripts":[63,75],"from":[64,126],"different":[65],"speakers.":[66],"use":[68],"L2":[71],"loss":[72,86],"prevent":[74],"align":[77],"wrong":[79],"speakers'":[80],"audio,":[81],"speaker":[84,89],"embedding":[85],"facilitate":[88],"tracking.":[90],"show":[92],"these":[96],"additional":[97],"training":[98],"objectives,":[99],"proposed":[101],"augmented":[102],"be":[106],"trained":[107],"with":[108],"simulated":[109],"overlapping":[110,123,144],"data":[112],"achieve":[115],"WER":[117,155],"32%":[119],"words":[121],"in":[122],"segments":[125],"real-life":[127],"telephone":[128],"conversations.":[129],"Our":[130],"analysis":[131],"manual":[133],"transcription":[134],"task":[135],"test":[139],"set":[140],"shows":[141],"transcribing":[143],"is":[146],"hard":[147],"even":[148],"humans":[150],"who":[151],"get":[153],"37%":[157],"compared":[158],"ground-truth.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}