{"id":"https://openalex.org/W4372262809","doi":"https://doi.org/10.1109/icassp49357.2023.10096081","title":"Universal Speaker Recognition Encoders for Different Speech Segments Duration","display_name":"Universal Speaker Recognition Encoders for Different Speech Segments Duration","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262809","doi":"https://doi.org/10.1109/icassp49357.2023.10096081"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096081","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096081","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/A5109435545","display_name":"Sergey Novoselov","orcid":"https://orcid.org/0009-0009-9354-8967"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Novoselov","raw_affiliation_strings":["ITMO University,St.Petersburg,Russia","STC Ltd., St.Petersburg, Russia","ITMO University, St.Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St.Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"STC Ltd., St.Petersburg, Russia","institution_ids":[]},{"raw_affiliation_string":"ITMO University, St.Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084186518","display_name":"Vladimir Volokhov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Volokhov","raw_affiliation_strings":["ITMO University,St.Petersburg,Russia","ITMO University, St.Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St.Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"ITMO University, St.Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047323209","display_name":"Galina Lavrentyeva","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Galina Lavrentyeva","raw_affiliation_strings":["ITMO University,St.Petersburg,Russia","ITMO University, St.Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St.Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"ITMO University, St.Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":0.6452,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73727344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"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":0.9916999936103821,"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":0.791480541229248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7735177278518677},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7051328420639038},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6444805860519409},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5711026191711426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5637710690498352},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5358437895774841},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5048971772193909},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5001168251037598},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4640587568283081},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4529886543750763},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4319360852241516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42175647616386414},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42102402448654175},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4159150719642639}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791480541229248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7735177278518677},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7051328420639038},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6444805860519409},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5711026191711426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5637710690498352},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5358437895774841},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5048971772193909},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5001168251037598},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4640587568283081},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4529886543750763},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4319360852241516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42175647616386414},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42102402448654175},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4159150719642639},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096081","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096081","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/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2404617565","https://openalex.org/W2726515241","https://openalex.org/W2933138175","https://openalex.org/W2963576203","https://openalex.org/W2972386477","https://openalex.org/W3024541814","https://openalex.org/W3024880099","https://openalex.org/W3025515949","https://openalex.org/W3036601975","https://openalex.org/W3198275944","https://openalex.org/W3202370288","https://openalex.org/W3205519288","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4283078310","https://openalex.org/W4283078911","https://openalex.org/W4288091954","https://openalex.org/W4297808394","https://openalex.org/W6769178842","https://openalex.org/W6787335539","https://openalex.org/W6802173870","https://openalex.org/W6804030475"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Creating":[0],"universal":[1,81,96,125],"speaker":[2,34,82,97,128],"encoders":[3,83],"which":[4],"are":[5,29,42],"robust":[6],"for":[7,31,44,69,84,94,99,117],"different":[8,85,134],"acoustic":[9],"and":[10,36,55,65,71,120,136],"speech":[11,27,57,86,138],"duration":[12],"conditions":[13],"is":[14,148],"a":[15],"big":[16],"challenge":[17],"today.":[18],"According":[19,107],"to":[20,108],"our":[21,91,109],"observations":[22],"systems":[23,37,115],"trained":[24,38,50],"on":[25,39,52],"short":[26,32,54,70],"segments":[28,41,46,58,87],"optimal":[30,62],"phrase":[33],"verification":[35,63,129],"long":[40,45,56,72],"superior":[43],"verification.":[47],"A":[48],"system":[49],"simultaneously":[51],"pooled":[53],"does":[59],"not":[60],"give":[61],"results":[64,111],"usually":[66],"degrades":[67],"both":[68],"segments.":[73],"This":[74],"paper":[75],"addresses":[76],"the":[77,123,145,152,157],"problem":[78],"of":[79,102,112,133,144],"creating":[80],"duration.":[88,140],"We":[89],"describe":[90],"simple":[92],"recipe":[93],"training":[95],"encoder":[98,126,147],"any":[100],"type":[101],"selected":[103,158],"neural":[104,159],"network":[105,160],"architecture.":[106,161],"evaluation":[110],"wav2vec-TDNN":[113],"based":[114],"obtained":[116],"NIST":[118],"SRE":[119],"VoxCeleb1":[121],"benchmarks":[122],"proposed":[124,146],"provides":[127],"improvements":[130],"in":[131],"case":[132],"enrollment":[135],"test":[137],"segment":[139],"The":[141],"key":[142],"feature":[143],"that":[149],"it":[150],"has":[151],"same":[153],"inference":[154],"time":[155],"as":[156]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}