{"id":"https://openalex.org/W3179294409","doi":"https://doi.org/10.1109/asru51503.2021.9687870","title":"Multi-User Voicefilter-Lite via Attentive Speaker Embedding","display_name":"Multi-User Voicefilter-Lite via Attentive Speaker Embedding","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3179294409","doi":"https://doi.org/10.1109/asru51503.2021.9687870","mag":"3179294409"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687870","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.01201","any_repository_has_fulltext":true},"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/A5101887853","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0003-1051-8287"},"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/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"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/A5101319167","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":0.61309853,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7012987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.8271740674972534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7973693609237671},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7613583207130432},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7548835873603821},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6306171417236328},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5417483448982239},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4536804258823395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41225725412368774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3303074836730957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271740674972534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7973693609237671},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7613583207130432},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7548835873603821},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6306171417236328},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5417483448982239},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4536804258823395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41225725412368774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3303074836730957},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9687870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687870","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.01201","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.01201","pdf_url":"https://arxiv.org/pdf/2107.01201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3179294409","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2107.01201","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2107.01201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.01201","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.01201","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.01201","pdf_url":"https://arxiv.org/pdf/2107.01201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3179294409.pdf","grobid_xml":"https://content.openalex.org/works/W3179294409.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2110075977","https://openalex.org/W2136439176","https://openalex.org/W2460742184","https://openalex.org/W2497335382","https://openalex.org/W2527729766","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2749510669","https://openalex.org/W2787692317","https://openalex.org/W2891833136","https://openalex.org/W2894279617","https://openalex.org/W2920796740","https://openalex.org/W2937769560","https://openalex.org/W2946508582","https://openalex.org/W2952634710","https://openalex.org/W2962760690","https://openalex.org/W2962788625","https://openalex.org/W2963403868","https://openalex.org/W2964238697","https://openalex.org/W2972362771","https://openalex.org/W2973062255","https://openalex.org/W2975044525","https://openalex.org/W3008181812","https://openalex.org/W3015598461","https://openalex.org/W3016361963","https://openalex.org/W3024085360","https://openalex.org/W3044278286","https://openalex.org/W3094979271","https://openalex.org/W3096090308","https://openalex.org/W3097643313","https://openalex.org/W3103434036","https://openalex.org/W3116025434","https://openalex.org/W3148416164","https://openalex.org/W3158180975","https://openalex.org/W3161354387","https://openalex.org/W3190394743","https://openalex.org/W3196705076","https://openalex.org/W3197845638","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6738243166","https://openalex.org/W6739901393","https://openalex.org/W6743590492","https://openalex.org/W6745415975","https://openalex.org/W6745983287","https://openalex.org/W6768205276","https://openalex.org/W6780404847","https://openalex.org/W6782435814","https://openalex.org/W6784687780"],"related_works":["https://openalex.org/W2056178548","https://openalex.org/W2483682256","https://openalex.org/W1586818475","https://openalex.org/W2907480510","https://openalex.org/W2973051376","https://openalex.org/W2341723397","https://openalex.org/W3205925339","https://openalex.org/W2105439218","https://openalex.org/W1867663770","https://openalex.org/W2984752753","https://openalex.org/W2556470078","https://openalex.org/W3200187816","https://openalex.org/W2169759054","https://openalex.org/W3135242330","https://openalex.org/W2025526713","https://openalex.org/W1737093455","https://openalex.org/W2062526508","https://openalex.org/W1595176759","https://openalex.org/W331744877","https://openalex.org/W2971680191"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,25,42,51,68,76,83,99],"solution":[6],"to":[7,16,40,54,91,108,116,147],"allow":[8],"speaker":[9,38,78,122,139],"conditioned":[10],"speech":[11,71,119],"models,":[12],"such":[13,151],"as":[14,50,152],"VoiceFilter-Lite,":[15],"support":[17],"an":[18,33],"arbitrary":[19],"number":[20],"of":[21],"enrolled":[22,96,110],"users":[23,97],"in":[24,98],"single":[26,43],"pass.":[27],"This":[28,137],"is":[29,47,114,127],"achieved":[30],"by":[31],"using":[32],"attention":[34],"mechanism":[35],"on":[36],"multiple":[37,95],"embeddings":[39],"compute":[41],"attentive":[44,138],"embedding,":[45],"which":[46],"then":[48],"used":[49],"side":[52],"input":[53],"the":[55],"model.":[56],"We":[57],"implemented":[58],"multi-user":[59,112],"VoiceFilter-Lite":[60,113],"and":[61,81,121,155],"evaluated":[62],"it":[63],"for":[64],"three":[65],"tasks:":[66],"(1)":[67],"streaming":[69],"automatic":[70],"recognition":[72,120],"(ASR)":[73],"task;":[74,80],"(2)":[75],"text-independent":[77],"verification":[79,123],"(3)":[82],"personalized":[84,156],"keyphrase":[85],"detection":[86],"task,":[87],"where":[88],"ASR":[89],"has":[90],"detect":[92],"keyphrases":[93],"from":[94],"noisy":[100],"environment.":[101],"Our":[102],"experiments":[103],"show":[104],"that,":[105],"with":[106],"up":[107],"four":[109],"users,":[111],"able":[115],"significantly":[117],"reduce":[118],"errors":[124],"when":[125],"there":[126],"overlapping":[128],"speech,":[129],"without":[130],"affecting":[131],"performance":[132],"under":[133],"other":[134,148],"acoustic":[135],"conditions.":[136],"embedding":[140],"approach":[141],"can":[142],"also":[143],"be":[144],"easily":[145],"applied":[146],"speaker-conditioned":[149],"models":[150],"personal":[153],"VAD":[154],"ASR.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}