{"id":"https://openalex.org/W3196415493","doi":"https://doi.org/10.1109/tsp52935.2021.9522589","title":"On Deep Speaker Embeddings for Speaker Verification","display_name":"On Deep Speaker Embeddings for Speaker Verification","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3196415493","doi":"https://doi.org/10.1109/tsp52935.2021.9522589","mag":"3196415493"},"language":"en","primary_location":{"id":"doi:10.1109/tsp52935.2021.9522589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","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/A5081210921","display_name":"Maro\u0161 Jakubec","orcid":"https://orcid.org/0000-0001-6231-0926"},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]},{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK","SK"],"is_corresponding":true,"raw_author_name":"Maros Jakubec","raw_affiliation_strings":["FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic"],"affiliations":[{"raw_affiliation_string":"FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic","institution_ids":["https://openalex.org/I3122011922","https://openalex.org/I1323252656"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083018341","display_name":"Roman Jarina","orcid":"https://orcid.org/0000-0002-0478-5808"},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]},{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK","SK"],"is_corresponding":false,"raw_author_name":"Roman Jarina","raw_affiliation_strings":["FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic"],"affiliations":[{"raw_affiliation_string":"FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic","institution_ids":["https://openalex.org/I3122011922","https://openalex.org/I1323252656"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004026604","display_name":"Eva Lieskovsk\u00e1","orcid":"https://orcid.org/0000-0002-7774-4994"},"institutions":[{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]},{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK","SK"],"is_corresponding":false,"raw_author_name":"Eva Lieskovska","raw_affiliation_strings":["FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic"],"affiliations":[{"raw_affiliation_string":"FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic","institution_ids":["https://openalex.org/I3122011922","https://openalex.org/I1323252656"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071100852","display_name":"Michal Chmul\u00edk","orcid":"https://orcid.org/0000-0002-0513-5129"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I3122011922","display_name":"University of \u017dilina","ror":"https://ror.org/031wwwj55","country_code":"SK","type":"education","lineage":["https://openalex.org/I3122011922"]}],"countries":["PK","SK"],"is_corresponding":false,"raw_author_name":"Michal Chmulik","raw_affiliation_strings":["FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic"],"affiliations":[{"raw_affiliation_string":"FEIT Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovak Republic","institution_ids":["https://openalex.org/I3122011922","https://openalex.org/I1323252656"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081210921"],"corresponding_institution_ids":["https://openalex.org/I1323252656","https://openalex.org/I3122011922"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72704433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8306288719177246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755333423614502},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.669745922088623},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6593567728996277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6371868848800659},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6040173768997192},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.557164192199707},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5190094709396362},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5180535316467285},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5118486285209656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4793485105037689},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4558597207069397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4469262957572937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10762038826942444}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8306288719177246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755333423614502},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.669745922088623},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6593567728996277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6371868848800659},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6040173768997192},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.557164192199707},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5190094709396362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5180535316467285},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5118486285209656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4793485105037689},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4558597207069397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4469262957572937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10762038826942444},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp52935.2021.9522589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W102958777","https://openalex.org/W128628490","https://openalex.org/W2046056978","https://openalex.org/W2078169166","https://openalex.org/W2114925438","https://openalex.org/W2183016404","https://openalex.org/W2185814970","https://openalex.org/W2290689761","https://openalex.org/W2402626018","https://openalex.org/W2587150483","https://openalex.org/W2718701456","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2794506738","https://openalex.org/W2805332618","https://openalex.org/W2805504157","https://openalex.org/W2916301830","https://openalex.org/W2940070181","https://openalex.org/W2962751625","https://openalex.org/W3097633443","https://openalex.org/W6605273041","https://openalex.org/W6686687092","https://openalex.org/W6712908891","https://openalex.org/W6762241601","https://openalex.org/W6785253293"],"related_works":["https://openalex.org/W4300326282","https://openalex.org/W2742395793","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W2810018382","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506"],"abstract_inverted_index":{"In":[0,48],"recent":[1,49],"years,":[2,50],"there":[3],"has":[4],"been":[5],"a":[6,40,104],"tremendous":[7],"application":[8],"spike":[9],"in":[10,21],"the":[11,28,66,72,84,101,112,124],"field":[12],"of":[13,30,43,71,103],"deep":[14],"neural":[15],"networks":[16],"(DNN),":[17],"including":[18],"increasing":[19],"interest":[20],"automatic":[22],"speaker":[23,32],"recognition":[24],"systems":[25,74],"development.":[26],"Currently,":[27],"utilization":[29],"DNN-based":[31,96],"embeddings,":[33],"such":[34],"as":[35],"x-vectors":[36,90],"or":[37],"d-vectors,":[38],"is":[39],"common":[41],"way":[42],"creating":[44],"speaker-specific":[45],"acoustic":[46],"models.":[47],"these":[51,76],"DNN":[52],"embedings":[53],"have":[54],"begun":[55],"to":[56],"replace":[57],"standard":[58],"i-vectors":[59,94],"extracted":[60],"by":[61],"factor":[62],"analysis.":[63],"We":[64,108],"evaluated":[65],"performance":[67],"and":[68,95,120],"training":[69],"time":[70],"developed":[73],"utilising":[75],"three":[77],"state-of-the-art":[78],"approaches.":[79],"The":[80],"results":[81],"obtained":[82],"on":[83],"VoxCeleb1":[85],"evaluation":[86],"set":[87],"show":[88,110],"that":[89,111],"outperformed":[91],"both":[92],"conventional":[93],"d-vectors":[97],"solutions,":[98],"however":[99],"at":[100],"cost":[102],"higher":[105],"computational":[106],"load.":[107],"also":[109],"x-vector":[113],"system":[114],"with":[115],"attentive":[116],"pooling,":[117],"AM-Softmax":[118],"activation":[119],"PLDA":[121],"back-end":[122],"gives":[123],"lowest":[125],"error":[126],"rate":[127],"over":[128],"other":[129],"architectures.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
