{"id":"https://openalex.org/W3025515949","doi":"https://doi.org/10.21437/odyssey.2020-26","title":"Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances","display_name":"Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3025515949","doi":"https://doi.org/10.21437/odyssey.2020-26","mag":"3025515949"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-26","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-26","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","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/A5102708099","display_name":"Aleksei Gusev","orcid":"https://orcid.org/0009-0001-5200-747X"},"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":"Aleksei Gusev","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","STC-innovations Ltd., 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-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084186518","display_name":"Vladimir Volokhov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Volokhov","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013243911","display_name":"Tseren Andzhukaev","orcid":"https://orcid.org/0009-0006-7415-2236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tseren Andzhukaev","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"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":["STC-innovations Ltd., St. Petersburg, Russia","ITMO University, St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations 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/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":["STC-innovations Ltd., St. Petersburg, Russia","ITMO University, St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations 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/A5034644396","display_name":"Marina Volkova","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":"Marina Volkova","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","STC-innovations Ltd., 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-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012552838","display_name":"Alice Gazizullina","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":"Alice Gazizullina","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","STC-innovations Ltd., 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-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072778309","display_name":"Andrey Shulipa","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":"Andrey Shulipa","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/A5064207791","display_name":"Artem Gorlanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artem Gorlanov","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088197786","display_name":"Anastasia Avdeeva","orcid":"https://orcid.org/0000-0001-7368-6099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anastasia Avdeeva","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275304","display_name":"Artem Ivanov","orcid":"https://orcid.org/0009-0001-6576-6547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artem Ivanov","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017762152","display_name":"Alexander Kozlov","orcid":"https://orcid.org/0000-0001-7650-0616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Kozlov","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029036362","display_name":"Timur Pekhovsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timur Pekhovsky","raw_affiliation_strings":["STC-innovations Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STC-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043808428","display_name":"Yuri Matveev","orcid":"https://orcid.org/0000-0001-7010-1585"},"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":"Yuri Matveev","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","STC-innovations Ltd., 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-innovations Ltd., St. Petersburg, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0102,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.9607558,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"186"},"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":0.9993000030517578,"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":0.996399998664856,"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":0.8384215831756592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7415438890457153},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.73659348487854},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.672208309173584},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6269422173500061},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.6207976341247559},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.583541989326477},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5313081741333008},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4431668817996979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4316670298576355},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41793274879455566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384215831756592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7415438890457153},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.73659348487854},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.672208309173584},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6269422173500061},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.6207976341247559},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.583541989326477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5313081741333008},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4431668817996979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4316670298576355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41793274879455566},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2020-26","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-26","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1498305593","https://openalex.org/W1901129140","https://openalex.org/W2117678320","https://openalex.org/W2164502538","https://openalex.org/W2194775991","https://openalex.org/W2406312423","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2747024632","https://openalex.org/W2748488820","https://openalex.org/W2807373279","https://openalex.org/W2808631503","https://openalex.org/W2889045432","https://openalex.org/W2916104401","https://openalex.org/W2938358845","https://openalex.org/W2962914239","https://openalex.org/W2963040451","https://openalex.org/W2963077989","https://openalex.org/W2963466847","https://openalex.org/W2963576203","https://openalex.org/W2972311940","https://openalex.org/W2972392008","https://openalex.org/W2972609576","https://openalex.org/W2972627751","https://openalex.org/W2972821391","https://openalex.org/W2973147881","https://openalex.org/W2979593053","https://openalex.org/W2981087920","https://openalex.org/W2998236288","https://openalex.org/W3103152812","https://openalex.org/W3166898278","https://openalex.org/W4245657124","https://openalex.org/W4288091954","https://openalex.org/W4288558760","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W468945283","https://openalex.org/W4247736853","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker":[0],"recognition":[1],"systems":[2,87],"based":[3,113],"on":[4,53,114],"deep":[5,109],"speaker":[6,51,85,148],"embeddings":[7],"have":[8],"achieved":[9],"significant":[10],"performance":[11],"in":[12,39,56,88,145],"controlled":[13],"conditions":[14,60],"according":[15],"to":[16,75],"the":[17,28,36,64,81,89,98,141,159,185],"results":[18,135,174],"obtained":[19],"for":[20,102,151,177,184],"early":[21],"NIST":[22],"SRE":[23],"(Speaker":[24],"Recognition":[25],"Evaluation)":[26],"datasets.From":[27],"practical":[29],"point":[30],"of":[31,63,83,91,147,161],"view,":[32],"taking":[33],"into":[34],"account":[35],"increased":[37],"interest":[38],"virtual":[40],"assistants":[41],"(such":[42],"as":[43],"Amazon":[44],"Alexa,":[45],"Google":[46],"Home,":[47],"Apple":[48],"Siri,":[49],"etc.),":[50],"verification":[52,86,149,182],"short":[54,103],"utterances":[55],"uncontrolled":[57],"noisy":[58],"environment":[59],"is":[61],"one":[62],"most":[65],"challenging":[66],"and":[67,95,120,131,154,169,181,188],"highly":[68],"demanded":[69],"tasks.This":[70],"paper":[71],"presents":[72],"approaches":[73],"aimed":[74],"achieve":[76],"two":[77],"goals:":[78],"a)":[79],"improve":[80],"quality":[82,100,150],"far-field":[84],"presence":[90],"environmental":[92],"noise,":[93],"reverberation":[94],"b)":[96],"reduce":[97],"system":[99],"degradation":[101],"utterances.For":[104],"these":[105],"purposes,":[106],"we":[107],"considered":[108],"neural":[110],"network":[111],"architectures":[112,139],"TDNN":[115],"(Time":[116],"Delay":[117],"Neural":[118,123],"Network)":[119,124],"ResNet":[121,138],"(Residual":[122],"blocks.We":[125],"experimented":[126],"with":[127],"state-of-the-art":[128],"embedding":[129],"extractors":[130],"their":[132],"training":[133],"procedures.Obtained":[134],"confirm":[136],"that":[137],"outperform":[140],"standard":[142],"x-vector":[143],"approach":[144],"terms":[146],"both":[152],"longduration":[153],"short-duration":[155],"utterances.We":[156],"also":[157],"investigate":[158],"impact":[160],"speech":[162],"activity":[163],"detector,":[164],"different":[165],"scoring":[166],"models,":[167],"adaptation":[168],"score":[170],"normalization":[171],"techniques.The":[172],"experimental":[173],"are":[175],"presented":[176],"publicly":[178],"available":[179],"data":[180],"protocols":[183],"VoxCeleb1,":[186],"VoxCeleb2,":[187],"VOiCES":[189],"datasets.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
