{"id":"https://openalex.org/W4226439436","doi":"https://doi.org/10.1109/icassp43922.2022.9747613","title":"OpenFEAT: Improving Speaker Identification by Open-Set Few-Shot Embedding Adaptation with Transformer","display_name":"OpenFEAT: Improving Speaker Identification by Open-Set Few-Shot Embedding Adaptation with Transformer","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226439436","doi":"https://doi.org/10.1109/icassp43922.2022.9747613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747613","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.12349","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109496249","display_name":"K C Kishan","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K C Kishan","raw_affiliation_strings":["Rochester Institute of Technology,Rochester,NY,USA","Rochester Institute of Technology, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology,Rochester,NY,USA","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","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":false,"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/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"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":"Long Chen","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/A5111963397","display_name":"Minho Jin","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":"Minho Jin","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":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056081738","display_name":"Chul Lee","orcid":"https://orcid.org/0000-0001-9329-7365"},"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":"Chul Lee","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":7,"corresponding_author_ids":["https://openalex.org/A5109496249"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":1.0471,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78035724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7062","last_page":"7066"},"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":0.9997000098228455,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.832854151725769},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6237354874610901},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6066996455192566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5985979437828064},{"id":"https://openalex.org/keywords/open-set","display_name":"Open set","score":0.5974060297012329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5799418091773987},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5211610794067383},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.483750581741333},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4586624205112457},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.425419420003891},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4229554235935211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3736329674720764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2184586226940155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09734955430030823}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.832854151725769},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6237354874610901},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6066996455192566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985979437828064},{"id":"https://openalex.org/C42357961","wikidata":"https://www.wikidata.org/wiki/Q213363","display_name":"Open set","level":2,"score":0.5974060297012329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5799418091773987},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5211610794067383},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.483750581741333},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4586624205112457},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.425419420003891},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4229554235935211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3736329674720764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2184586226940155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09734955430030823},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747613","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.12349","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.12349","pdf_url":"https://arxiv.org/pdf/2202.12349","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:2202.12349","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.12349","pdf_url":"https://arxiv.org/pdf/2202.12349","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":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2652009","https://openalex.org/W1589137271","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2753160622","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2963341924","https://openalex.org/W3013020904","https://openalex.org/W3024144824","https://openalex.org/W3024541814","https://openalex.org/W3034312118","https://openalex.org/W3035654071","https://openalex.org/W3090254849","https://openalex.org/W3092956463","https://openalex.org/W3197845638","https://openalex.org/W4385245566","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6739901393","https://openalex.org/W6740167877","https://openalex.org/W6743661861","https://openalex.org/W6783527727"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2997567050","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2088247287","https://openalex.org/W3006008237"],"abstract_inverted_index":{"Household":[0],"speaker":[1,45,56,74,94,111],"identification":[2,42,57,95,112],"with":[3,104,120],"few":[4],"enrollment":[5],"utterances":[6],"is":[7,35,126],"an":[8],"important":[9],"yet":[10],"challenging":[11],"problem,":[12],"especially":[13],"when":[14],"household":[15,55,93],"members":[16],"share":[17],"similar":[18],"voice":[19],"characteristics":[20],"and":[21,64],"room":[22],"acoustics.":[23],"A":[24],"common":[25],"embedding":[26,69,80,85],"space":[27,81,86],"learned":[28],"from":[29,76],"a":[30,47,59,67,83,88],"large":[31],"number":[32],"of":[33,43],"speakers":[34,125],"not":[36],"universally":[37],"applicable":[38],"for":[39],"the":[40,77,110],"optimal":[41],"every":[44],"in":[46],"household.":[48],"In":[49],"this":[50],"work,":[51],"we":[52,107],"first":[53],"formulate":[54],"as":[58],"few-shot":[60],"open-set":[61],"recognition":[62],"task":[63],"then":[65],"propose":[66],"novel":[68],"adaptation":[70],"framework":[71],"to":[72,82,122,130],"adapt":[73],"representations":[75],"given":[78],"universal":[79],"household-specific":[84],"using":[87],"set-to-set":[89],"function,":[90],"yielding":[91],"better":[92],"performance.":[96],"With":[97],"our":[98],"algorithm,":[99],"Open-set":[100],"Few-shot":[101],"Embedding":[102],"Adaptation":[103],"Transformer":[105],"(openFEAT),":[106],"observe":[108],"that":[109],"equal":[113],"error":[114],"rate":[115],"(IEER)":[116],"on":[117],"simulated":[118],"households":[119],"2":[121],"7":[123],"hard-to-discriminate":[124],"reduced":[127],"by":[128],"23%":[129],"31%":[131],"relative.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-05-05T00:00:00"}