{"id":"https://openalex.org/W3097201508","doi":"https://doi.org/10.21437/interspeech.2020-2430","title":"Identify Speakers in Cocktail Parties with End-to-End Attention","display_name":"Identify Speakers in Cocktail Parties with End-to-End Attention","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097201508","doi":"https://doi.org/10.21437/interspeech.2020-2430","mag":"3097201508"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2430","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":"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/A5048524258","display_name":"Junzhe Zhu","orcid":"https://orcid.org/0000-0002-4316-8570"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junzhe Zhu","raw_affiliation_strings":["ECE Department, University of Illinois, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, University of Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["ECE Department, University of Illinois, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, University of Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003052411","display_name":"Leda Sar\u0131","orcid":"https://orcid.org/0000-0002-3754-1156"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leda Sar\u0131","raw_affiliation_strings":["ECE Department, University of Illinois, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, University of Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048524258"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3092","last_page":"3096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9988999962806702,"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":0.9986000061035156,"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":0.8918212056159973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6219149827957153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4027841091156006},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.27698609232902527}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8918212056159973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219149827957153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4027841091156006},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.27698609232902527}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2430","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":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W29573733","https://openalex.org/W1481646516","https://openalex.org/W1519545362","https://openalex.org/W1639266067","https://openalex.org/W1790748249","https://openalex.org/W1865095259","https://openalex.org/W1901129140","https://openalex.org/W2044222806","https://openalex.org/W2079362249","https://openalex.org/W2106934198","https://openalex.org/W2123879651","https://openalex.org/W2148295152","https://openalex.org/W2150769028","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2460742184","https://openalex.org/W2890111732","https://openalex.org/W2890354241","https://openalex.org/W2891355459","https://openalex.org/W2936794852","https://openalex.org/W2952218014","https://openalex.org/W2962858469","https://openalex.org/W2963495494","https://openalex.org/W2964607787","https://openalex.org/W3016042119","https://openalex.org/W3016131876","https://openalex.org/W4243233711","https://openalex.org/W4288089163","https://openalex.org/W4289665794"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"scenarios":[1,121],"where":[2],"multiple":[3],"speakers":[4,110,118],"talk":[5],"at":[6],"the":[7,18,47,51,65],"same":[8],"time,":[9],"it":[10],"is":[11],"important":[12],"to":[13,16,39,57,83],"be":[14],"able":[15],"identify":[17],"talkers":[19],"accurately.This":[20],"paper":[21],"presents":[22],"an":[23],"end-to-end":[24],"system":[25,94],"that":[26,61,95,115],"integrates":[27],"speech":[28,103],"source":[29],"extraction":[30],"and":[31,34,108,114],"speaker":[32,48,68,98],"identification,":[33,69],"proposes":[35],"a":[36,78,93,100],"new":[37],"way":[38],"jointly":[40],"optimize":[41],"these":[42],"two":[43],"parts":[44],"by":[45],"max-pooling":[46],"predictions":[49],"along":[50],"channel":[52],"dimension.Residual":[53],"attention":[54],"permits":[55],"us":[56],"learn":[58],"spectrogram":[59],"masks":[60],"are":[62],"optimized":[63],"for":[64],"purpose":[66],"of":[67],"while":[70],"residual":[71],"forward":[72],"connections":[73],"permit":[74],"dilated":[75],"convolution":[76],"with":[77,105,111,122],"sufficiently":[79],"large":[80],"context":[81],"window":[82],"guarantee":[84],"correct":[85],"streaming":[86],"across":[87],"syllable":[88],"boundaries.End-to-end":[89],"training":[90],"results":[91],"in":[92,99,119],"recognizes":[96,116],"one":[97],"two-speaker":[101],"broadcast":[102],"mixture":[104],"99.9%":[106],"accuracy":[107],"both":[109],"93.9%":[112],"accuracy,":[113],"all":[117],"three-speaker":[120],"81.2%":[123],"accuracy.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}