{"id":"https://openalex.org/W4283069943","doi":"https://doi.org/10.21437/odyssey.2022-41","title":"Closing the Gap Between Single-User and Multi-User VoiceFilter-Lite","display_name":"Closing the Gap Between Single-User and Multi-User VoiceFilter-Lite","publication_year":2022,"publication_date":"2022-06-17","ids":{"openalex":"https://openalex.org/W4283069943","doi":"https://doi.org/10.21437/odyssey.2022-41"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2022-41","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2022)","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/A5003481800","display_name":"Rajeev Rikhye","orcid":"https://orcid.org/0000-0003-2011-2897"},"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":"Rajeev Rikhye","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418245","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6102-3407"},"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":"Quan Wang","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308586","display_name":"Qiao Liang","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":"Qiao Liang","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153566","display_name":"Yanzhang He","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":"Yanzhang He","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","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":"Ian McGraw","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003481800"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3979,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65846121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"294","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9420999884605408,"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/T12031","display_name":"Speech and dialogue systems","score":0.9420999884605408,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.7649401426315308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328269839286804},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3263152539730072},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.1026742160320282}],"concepts":[{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.7649401426315308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328269839286804},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3263152539730072},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1026742160320282},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2022-41","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2022)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2136439176","https://openalex.org/W2497335382","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2749510669","https://openalex.org/W2760103357","https://openalex.org/W2787692317","https://openalex.org/W2891833136","https://openalex.org/W2962760690","https://openalex.org/W2962788625","https://openalex.org/W2963596039","https://openalex.org/W2964238697","https://openalex.org/W2972362771","https://openalex.org/W2973062255","https://openalex.org/W2975044525","https://openalex.org/W3024085360","https://openalex.org/W3096090308","https://openalex.org/W3097643313","https://openalex.org/W3103434036","https://openalex.org/W3112702554","https://openalex.org/W3112929926","https://openalex.org/W3161354387","https://openalex.org/W3196705076","https://openalex.org/W3197845638","https://openalex.org/W4225742484","https://openalex.org/W4226191785","https://openalex.org/W4226428303","https://openalex.org/W4286856942","https://openalex.org/W4384434594","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2517007886","https://openalex.org/W2383994331","https://openalex.org/W1522019333","https://openalex.org/W3121919567","https://openalex.org/W2076369646","https://openalex.org/W278047738","https://openalex.org/W4244817184","https://openalex.org/W2373884197"],"abstract_inverted_index":{"VoiceFilter-Lite":[0,87,110,144],"is":[1,37,49],"a":[2,9,45,102,113],"speaker-conditioned":[3,32],"voice":[4],"separation":[5],"model":[6,88,128,154,172],"that":[7,38],"plays":[8],"crucial":[10],"role":[11],"in":[12,35],"improving":[13],"speech":[14,22,33],"recognition":[15],"and":[16,30,79,118,142,166],"speaker":[17,76,132],"verification":[18],"by":[19,119],"suppressing":[20],"overlapping":[21],"from":[23,90],"non-target":[24],"speakers.However,":[25],"one":[26],"limitation":[27],"of":[28,66,104,164],"VoiceFilter-Lite,":[29],"other":[31],"models":[34,40,145],"general,":[36],"these":[39],"are":[41],"usually":[42],"limited":[43],"to":[44,62,68,82,106,125,160],"single":[46],"target":[47],"speaker.This":[48],"undesirable":[50],"as":[51],"most":[52],"smart":[53],"home":[54],"devices":[55],"now":[56],"support":[57,161],"multiple":[58,69],"enrolled":[59],"users.In":[60],"order":[61],"extend":[63],"the":[64,84,108,127,130,137,149,152],"benefits":[65],"personalization":[67],"users,":[70,165],"we":[71,100,134],"previously":[72,170],"developed":[73],"an":[74],"attention-based":[75],"selection":[77],"mechanism":[78],"applied":[80],"it":[81],"VoiceFilter-Lite.However,":[83],"original":[85],"multi-user":[86,109,141],"suffers":[89],"significant":[91],"performance":[92,138],"degradation":[93],"compared":[94],"with":[95,129],"single-user":[96,143],"models.In":[97],"this":[98],"paper,":[99],"devised":[101],"series":[103],"experiments":[105],"improve":[107],"model.By":[111],"incorporating":[112],"dual":[114],"learning":[115],"rate":[116],"schedule":[117],"using":[120],"feature-wise":[121],"linear":[122],"modulation":[123],"(FiLM)":[124],"condition":[126],"attended":[131],"embedding,":[133],"successfully":[135],"closed":[136],"gap":[139],"between":[140],"on":[146,173],"single-speaker":[147],"evaluations.At":[148],"same":[150],"time,":[151],"new":[153],"can":[155],"also":[156],"be":[157],"easily":[158],"extended":[159],"any":[162],"number":[163],"significantly":[167],"outperforms":[168],"our":[169],"published":[171],"multi-speaker":[174],"evaluations.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}