{"id":"https://openalex.org/W4392903874","doi":"https://doi.org/10.1109/icassp48485.2024.10447161","title":"Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models","display_name":"Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903874","doi":"https://doi.org/10.1109/icassp48485.2024.10447161"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447161","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5101425533","display_name":"Chenyang Gao","orcid":"https://orcid.org/0000-0002-0280-7882"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyang Gao","raw_affiliation_strings":["Rutgers, The State University of New Jersey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, The State University of New Jersey","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032699386","display_name":"Brecht Desplanques","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brecht Desplanques","raw_affiliation_strings":["Amazon Alexa AI,U.S.A","Amazon Alexa AI, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,U.S.A","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073504925","display_name":"Chelsea J.\u2010T. Ju","orcid":"https://orcid.org/0000-0001-8674-5318"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea J.-T. Ju","raw_affiliation_strings":["Amazon Alexa AI,U.S.A","Amazon Alexa AI, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,U.S.A","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047032131","display_name":"Aman Chadha","orcid":"https://orcid.org/0000-0001-6621-9003"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Chadha","raw_affiliation_strings":["Amazon Alexa AI,U.S.A","Amazon Alexa AI, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,U.S.A","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa AI,U.S.A","Amazon Alexa AI, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,U.S.A","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10836","last_page":"10840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.8209189176559448},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7271870374679565},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5286429524421692},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5073887705802917},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.46756038069725037},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.44545063376426697},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4275944232940674},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4243118166923523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31628721952438354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209189176559448},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7271870374679565},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5286429524421692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5073887705802917},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.46756038069725037},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.44545063376426697},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4275944232940674},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4243118166923523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31628721952438354},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447161","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W596281310","https://openalex.org/W2064675550","https://openalex.org/W2792643794","https://openalex.org/W2890964092","https://openalex.org/W2936733796","https://openalex.org/W2962788625","https://openalex.org/W2969985801","https://openalex.org/W3197845638","https://openalex.org/W3198604552","https://openalex.org/W3205519288","https://openalex.org/W4283078310","https://openalex.org/W4283078911","https://openalex.org/W4293363567","https://openalex.org/W4372262809","https://openalex.org/W6783797576","https://openalex.org/W6799764170"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205","https://openalex.org/W2150532155"],"abstract_inverted_index":{"Automated":[0],"speaker":[1,116,132,149],"identification":[2],"(SID)":[3],"is":[4],"a":[5,12,22,27,100,114,130,141],"crucial":[6],"step":[7],"for":[8,35,76,135],"the":[9,49,90,106,109,168,175,184],"personalization":[10],"of":[11,15,52,89,164,167,174],"wide":[13],"range":[14],"speech-enabled":[16],"services.":[17],"Typical":[18],"SID":[19,86,187],"systems":[20],"use":[21],"symmetric":[23,186],"enrollment-verification":[24,70],"framework":[25,71],"with":[26,140,147,160],"single":[28],"model":[29],"to":[30,48,104,113],"derive":[31],"embeddings":[32,107],"both":[33,181],"offline":[34],"voice":[36],"profiles":[37],"extracted":[38],"from":[39,44,67,108],"enrollment":[40,53,77],"utterances,":[41],"and":[42,54,60,78],"online":[43],"runtime":[45,79],"utterances.":[46],"Due":[47],"distinct":[50],"circumstances":[51],"runtime,":[55],"such":[56],"as":[57],"different":[58,74],"computation":[59],"latency":[61],"constraints,":[62],"several":[63],"applications":[64],"would":[65],"benefit":[66],"an":[68,161],"asymmetric":[69,85,162],"that":[72,122,137],"uses":[73],"models":[75,92,112,136,169,182],"embedding":[80,117],"generation.":[81],"To":[82],"support":[83],"this":[84,123],"where":[87],"each":[88],"two":[91,110],"can":[93],"be":[94],"updated":[95],"independently,":[96],"we":[97],"propose":[98],"using":[99],"lightweight":[101],"neural":[102],"network":[103],"map":[105],"independent":[111],"shared":[115,131],"space.":[118],"Our":[119],"results":[120],"show":[121],"approach":[124],"significantly":[125],"outperforms":[126],"cosine":[127],"scoring":[128],"in":[129,183],"logit":[133],"space":[134],"were":[138],"trained":[139],"contrastive":[142],"loss":[143],"on":[144],"large":[145],"datasets":[146],"many":[148],"identities.":[150],"This":[151],"proposed":[152],"Neural":[153],"Embedding":[154],"Speaker":[155],"Space":[156],"Alignment":[157],"(NESSA)":[158],"combined":[159],"update":[163],"only":[165],"one":[166],"delivers":[170],"at":[171],"least":[172],"60%":[173],"performance":[176],"gain":[177],"achieved":[178],"by":[179],"updating":[180],"standard":[185],"approach.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-03-19T00:00:00"}