{"id":"https://openalex.org/W3197142615","doi":"https://doi.org/10.1109/asru51503.2021.9687975","title":"Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets","display_name":"Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3197142615","doi":"https://doi.org/10.1109/asru51503.2021.9687975","mag":"3197142615"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687975","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.02576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064917138","display_name":"Zhenning Tan","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":true,"raw_author_name":"Zhenning Tan","raw_affiliation_strings":["Amazon Alexa AI,Sunnyvale,CA,USA","Amazon Alexa AI, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022888361","display_name":"Yuguang Yang","orcid":"https://orcid.org/0000-0002-9523-9254"},"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":"Yuguang Yang","raw_affiliation_strings":["Amazon Alexa AI,Sunnyvale,CA,USA","Amazon Alexa AI, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005681147","display_name":"Eun\u2010Jung Han","orcid":"https://orcid.org/0000-0002-8385-3775"},"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":"Eunjung Han","raw_affiliation_strings":["Amazon Alexa AI,Sunnyvale,CA,USA","Amazon Alexa AI, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, Sunnyvale, CA, USA","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,Sunnyvale,CA,USA","Amazon Alexa AI, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064917138"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.5077,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65696331,"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":"1124","last_page":"1131"},"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":0.9998999834060669,"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":0.9994999766349792,"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":0.7366867065429688},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7142612934112549},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6883399486541748},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.677585244178772},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6118196249008179},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5571107864379883},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5396032929420471},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5138533115386963},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4593442380428314},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.44991397857666016},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4485807716846466},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44397425651550293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4114704132080078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39768415689468384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366867065429688},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7142612934112549},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6883399486541748},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.677585244178772},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6118196249008179},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5571107864379883},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5396032929420471},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5138533115386963},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4593442380428314},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.44991397857666016},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4485807716846466},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44397425651550293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4114704132080078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39768415689468384},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru51503.2021.9687975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687975","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:2109.02576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.02576","pdf_url":"https://arxiv.org/pdf/2109.02576","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.02576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.02576","pdf_url":"https://arxiv.org/pdf/2109.02576","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2652009","https://openalex.org/W1589137271","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2162501025","https://openalex.org/W2289985966","https://openalex.org/W2406312423","https://openalex.org/W2535838896","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962369866","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2978426779","https://openalex.org/W3013020904","https://openalex.org/W3024098654","https://openalex.org/W3024144824","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3034312118","https://openalex.org/W3090254849","https://openalex.org/W3092956463","https://openalex.org/W3118062200","https://openalex.org/W3180562345","https://openalex.org/W3197845638","https://openalex.org/W3198104675","https://openalex.org/W4297687186","https://openalex.org/W6635152626","https://openalex.org/W6713727690","https://openalex.org/W6737575990","https://openalex.org/W6740167877","https://openalex.org/W6742911084","https://openalex.org/W6762913911","https://openalex.org/W6765939562","https://openalex.org/W6777607917","https://openalex.org/W6778102432","https://openalex.org/W6783527727"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W4234190324","https://openalex.org/W2162158162","https://openalex.org/W2545131480","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Speaker":[0],"identification":[1],"typically":[2],"involves":[3],"three":[4],"stages.":[5],"First,":[6],"a":[7,21,27,52,60,65],"front-end":[8],"speaker":[9,18,32,36,85,129],"embedding":[10],"model":[11,93],"is":[12,24,37,79,116],"trained":[13],"to":[14,43,64,69,103,138],"embed":[15],"utterance":[16,29],"and":[17,30,134],"profiles.":[19],"Second,":[20],"scoring":[22,45,73,77,92],"function":[23,78],"applied":[25],"between":[26],"runtime":[28],"each":[31],"profile.":[33],"Finally,":[34],"the":[35,44,55,71,90,113],"identified":[38],"using":[39],"nearest":[40],"neighbor":[41],"according":[42],"metric.":[46,74],"To":[47],"better":[48],"distinguish":[49],"speakers":[50,106],"sharing":[51],"device":[53],"within":[54],"same":[56],"household,":[57],"we":[58,121],"propose":[59],"household-adapted":[61,128],"nonlinear":[62],"mapping":[63],"low":[66],"dimensional":[67],"space":[68],"complement":[70],"global":[72,142],"The":[75],"combined":[76],"optimized":[80],"on":[81],"labeled":[82],"or":[83],"pseudo-labeled":[84],"utterances.":[86],"With":[87],"input":[88],"dropout,":[89],"proposed":[91],"reduces":[94],"EER":[95,114],"by":[96,127,141],"45\u201371%":[97],"in":[98],"simulated":[99],"households":[100],"with":[101],"2":[102],"7":[104],"hard-to-discriminate":[105],"per":[107],"household.":[108],"On":[109],"real-world":[110],"internal":[111],"data,":[112],"reduction":[115],"49.2%.":[117],"From":[118],"t-SNE":[119],"visualization,":[120],"also":[122],"show":[123],"that":[124],"clusters":[125,139],"formed":[126,140],"embeddings":[130,143],"are":[131],"more":[132],"compact":[133],"uniformly":[135],"distributed,":[136],"compared":[137],"before":[144],"adaptation.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
