{"id":"https://openalex.org/W4375868975","doi":"https://doi.org/10.1109/icassp49357.2023.10097032","title":"Probabilistic Back-ends for Online Speaker Recognition and Clustering","display_name":"Probabilistic Back-ends for Online Speaker Recognition and Clustering","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868975","doi":"https://doi.org/10.1109/icassp49357.2023.10097032"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5084640883","display_name":"Alexey Sholokhov","orcid":null},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"funder","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexey Sholokhov","raw_affiliation_strings":["Federal Research Center \"Computer Science and Control\" of the Russian Academy of Sciences,Moscow,Russia","Federal Research Center \"Computer Science and Control\" of the Russian Academy of Sciences, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\" of the Russian Academy of Sciences,Moscow,Russia","institution_ids":["https://openalex.org/I1313323035"]},{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\" of the Russian Academy of Sciences, Moscow, Russia","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080580365","display_name":"Nikita Kuzmin","orcid":"https://orcid.org/0000-0002-8260-7118"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nikita Kuzmin","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["A⋆STAR,Institute for Infocomm Research,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A⋆STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084640883"],"corresponding_institution_ids":["https://openalex.org/I1313323035"],"apc_list":null,"apc_paid":null,"fwci":0.5107,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70030048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9889000058174133,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8161211609840393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8006178736686707},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6537002921104431},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6352874040603638},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5833892822265625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5341649651527405},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5215242505073547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5079014897346497},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.48344168066978455},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4629654884338379},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4619716703891754},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34008699655532837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10211420059204102},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10048016905784607}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8161211609840393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006178736686707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6537002921104431},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6352874040603638},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5833892822265625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5341649651527405},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5215242505073547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5079014897346497},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.48344168066978455},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4629654884338379},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4619716703891754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34008699655532837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10211420059204102},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10048016905784607},{"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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.46000000834465027,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W61015563","https://openalex.org/W82277249","https://openalex.org/W1601795611","https://openalex.org/W1982353806","https://openalex.org/W2068004116","https://openalex.org/W2122899485","https://openalex.org/W2134706965","https://openalex.org/W2150769028","https://openalex.org/W2174668315","https://openalex.org/W2294814385","https://openalex.org/W2395619215","https://openalex.org/W2397336997","https://openalex.org/W2403536560","https://openalex.org/W2405137844","https://openalex.org/W2726515241","https://openalex.org/W2746871870","https://openalex.org/W2750001021","https://openalex.org/W2805960464","https://openalex.org/W2807429203","https://openalex.org/W2972449503","https://openalex.org/W2989790778","https://openalex.org/W3038871978","https://openalex.org/W3090254849","https://openalex.org/W3135243134","https://openalex.org/W3152426975","https://openalex.org/W3167533889","https://openalex.org/W3178462146","https://openalex.org/W3197142615","https://openalex.org/W4223531842","https://openalex.org/W4224795206","https://openalex.org/W4245490569","https://openalex.org/W4246202668","https://openalex.org/W4283030875","https://openalex.org/W4283076825","https://openalex.org/W4294589828","https://openalex.org/W4297841684","https://openalex.org/W6602473807","https://openalex.org/W6633847657","https://openalex.org/W6678297943","https://openalex.org/W6684028345","https://openalex.org/W6711976041","https://openalex.org/W6748447238","https://openalex.org/W6783527727","https://openalex.org/W6787874867"],"related_works":["https://openalex.org/W2250488071","https://openalex.org/W2356150353","https://openalex.org/W2380744779","https://openalex.org/W1999647744","https://openalex.org/W2018643641","https://openalex.org/W2469878540","https://openalex.org/W2765337000","https://openalex.org/W2967867994","https://openalex.org/W2112264450","https://openalex.org/W2078150608"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,57],"multi-enrollment":[4,77,103],"speaker":[5,15,95],"recognition":[6,78],"which":[7],"naturally":[8,101],"occurs":[9],"in":[10,25,84],"the":[11,19,73,81,85,117,122,134,137],"task":[12,97],"of":[13,21,44,62,87,136],"online":[14,94,108],"clustering,":[16],"and":[17,127],"studies":[18],"properties":[20],"different":[22],"scoring":[23,34,55,75],"back-ends":[24],"this":[26],"scenario.":[27],"First,":[28],"we":[29,48,91],"show":[30],"that":[31],"popular":[32],"cosine":[33,54,74],"suffers":[35],"from":[36,116],"poor":[37],"score":[38,129],"calibration":[39],"with":[40],"a":[41,50],"varying":[42],"number":[43],"enrollment":[45],"utterances.":[46],"Second,":[47],"propose":[49,106],"simple":[51],"replacement":[52],"for":[53,76],"based":[56],"an":[58,93,107],"extremely":[59],"constrained":[60],"version":[61],"probabilistic":[63],"linear":[64],"discriminant":[65],"analysis":[66],"(PLDA).":[67],"The":[68],"proposed":[69,138],"model":[70,119],"improves":[71],"over":[72],"while":[79],"keeping":[80],"same":[82],"performance":[83],"case":[86],"one-to-one":[88],"comparisons.":[89],"Finally,":[90],"consider":[92],"clustering":[96,109],"where":[98],"each":[99],"step":[100],"involves":[102],"recognition.":[104],"We":[105],"algorithm":[110],"allowing":[111],"us":[112],"to":[113,124],"take":[114],"benefits":[115],"PLDA":[118],"such":[120],"as":[121],"ability":[123],"handle":[125],"uncertainty":[126],"better":[128],"calibration.":[130],"Our":[131],"experiments":[132],"demonstrate":[133],"effectiveness":[135],"algorithm.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}