{"id":"https://openalex.org/W4408353275","doi":"https://doi.org/10.1109/icassp49660.2025.10889905","title":"In Search of Optimal Pretraining Strategy for Robust Speaker Recognition","display_name":"In Search of Optimal Pretraining Strategy for Robust Speaker Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353275","doi":"https://doi.org/10.1109/icassp49660.2025.10889905"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5092639584","display_name":"Nikita Khmelev","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":"Nikita Khmelev","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stepan Malykh","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":"Stepan Malykh","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alexandr Anikin","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":"Alexandr Anikin","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594415","display_name":"Anastasia Korenevskaya","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":"Anastasia Korenevskaya","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594416","display_name":"Zorkina Anastasia","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":"Zorkina Anastasia","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594417","display_name":"Vladislav Marchevskiy","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":"Vladislav Marchevskiy","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"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":1.0139,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7141199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"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/T10860","display_name":"Speech and Audio Processing","score":0.8820000290870667,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8820000290870667,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.859499990940094,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8127999901771545,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7114105224609375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6751296520233154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6367447376251221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4190458357334137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40357673168182373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114105224609375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6751296520233154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6367447376251221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4190458357334137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40357673168182373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2404617565","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2842511635","https://openalex.org/W2933138175","https://openalex.org/W2963587345","https://openalex.org/W2973049979","https://openalex.org/W2978904488","https://openalex.org/W2981087920","https://openalex.org/W3024869864","https://openalex.org/W3024880099","https://openalex.org/W3025515949","https://openalex.org/W3094374485","https://openalex.org/W3097777922","https://openalex.org/W3163059624","https://openalex.org/W3167533889","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225096077","https://openalex.org/W4283078310","https://openalex.org/W4312443924","https://openalex.org/W4319862271","https://openalex.org/W4372340947","https://openalex.org/W4385245566","https://openalex.org/W4385822708","https://openalex.org/W4385823321","https://openalex.org/W4385823373","https://openalex.org/W4386076493","https://openalex.org/W4392903478","https://openalex.org/W4400033122","https://openalex.org/W4402111453","https://openalex.org/W4402111578","https://openalex.org/W6688816777","https://openalex.org/W6748816842","https://openalex.org/W6755207826","https://openalex.org/W6767671539","https://openalex.org/W6780218876","https://openalex.org/W6803394801"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W2033914206","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W2042327336","https://openalex.org/W289407349","https://openalex.org/W2368768466"],"abstract_inverted_index":{"While":[0],"demonstrating":[1],"state-of-the-art":[2],"results":[3,93],"in":[4,19,108,123,147],"the":[5,39,54,68,74,85,128,142,163],"microphone":[6],"channel":[7,26],"domain":[8],"(VoxCeleb":[9],"protocols),":[10],"contemporary":[11],"speaker":[12,40,167],"verification":[13,41,168],"systems":[14,78],"are":[15,79],"not":[16],"often":[17],"tested":[18],"challenging":[20],"acoustic":[21],"environments":[22],"such":[23],"as":[24],"telephone":[25],"or":[27],"far-field":[28],"microphone.":[29],"This":[30],"paper":[31],"compares":[32],"modern":[33],"pretraining":[34,66,97,159],"strategies,":[35],"proven":[36],"beneficial":[37],"for":[38,144],"task.":[42],"It":[43],"follows":[44],"wav2vec":[45,115],"2.0,":[46],"HuBERT,":[47],"ASR":[48,96],"procedures,":[49],"and":[50,71,88],"aims":[51],"to":[52,104,127,139],"identify":[53],"most":[55],"effective,":[56],"robust":[57],"approach.":[58],"We":[59,131,150],"conduct":[60],"a":[61,119,155,158,166],"range":[62],"of":[63,114,135,157,165],"experiments":[64],"with":[65,84],"on":[67,73,81],"LibriSpeech":[69],"corpus":[70],"finetuning":[72],"VoxCeleb":[75],"dataset.":[76],"The":[77],"evaluated":[80],"multiple":[82],"protocols":[83],"microphone,":[86],"telephone,":[87],"cross-channel":[89],"tasks.":[90],"Our":[91],"empirical":[92],"show":[94],"that":[95,153],"demonstrates":[98],"superior":[99],"in-domain":[100],"performance":[101,146],"but":[102],"fails":[103],"match":[105],"HuBERT/wav2vec":[106],"2.0":[107,116],"out-of-domain":[109,124],"NIST":[110],"SRE":[111],"assessment.":[112],"Adoption":[113],"strategy":[117],"achieves":[118],"34%":[120],"average":[121],"improvement":[122],"evaluations":[125],"compared":[126],"baseline":[129],"systems.":[130],"employ":[132],"UMAP":[133],"visualization":[134],"models\u2019":[136],"embedding":[137],"space":[138],"further":[140],"understand":[141],"reasons":[143],"unstable":[145],"adversarial":[148],"conditions.":[149],"also":[151],"conclude":[152],"while":[154],"choice":[156],"scheme":[160],"is":[161,170],"important,":[162],"impact":[164],"backend":[169],"negligible.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}