{"id":"https://openalex.org/W2798824629","doi":"https://doi.org/10.21437/odyssey.2018-53","title":"On deep speaker embeddings for text-independent speaker recognition","display_name":"On deep speaker embeddings for text-independent speaker recognition","publication_year":2018,"publication_date":"2018-06-06","ids":{"openalex":"https://openalex.org/W2798824629","doi":"https://doi.org/10.21437/odyssey.2018-53","mag":"2798824629"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2018-53","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-53","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 2018)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.10080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109435545","display_name":"Sergey Novoselov","orcid":"https://orcid.org/0009-0009-9354-8967"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergey Novoselov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072778309","display_name":"Andrey Shulipa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrey Shulipa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057862767","display_name":"Ivan Kremnev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Kremnev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108707228","display_name":"Alexandr Kozlov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandr Kozlov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064716887","display_name":"Vadim Shchemelinin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vadim Shchemelinin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0152,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81566658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"385"},"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":0.9984999895095825,"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":0.9965000152587891,"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":0.8969002962112427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7989591360092163},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6741336584091187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6248908042907715},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5917414426803589},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5777422189712524},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5730413198471069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5477983951568604},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5317273139953613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5206372141838074},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.46954354643821716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4459741413593292},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4392995834350586},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4285675883293152},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42688286304473877},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.41851332783699036},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.41792556643486023}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8969002962112427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989591360092163},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6741336584091187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6248908042907715},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5917414426803589},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5777422189712524},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5730413198471069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5477983951568604},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5317273139953613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5206372141838074},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.46954354643821716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4459741413593292},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4392995834350586},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4285675883293152},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42688286304473877},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.41851332783699036},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41792556643486023},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/odyssey.2018-53","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-53","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 2018)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.10080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.10080","pdf_url":"https://arxiv.org/pdf/1804.10080","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2798824629","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.10080.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.10080","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.10080","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.10080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.10080","pdf_url":"https://arxiv.org/pdf/1804.10080","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321912","display_name":"Ministry of Education and Science of the Russian Federation","ror":"https://ror.org/00ghqgy32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798824629.pdf","grobid_xml":"https://content.openalex.org/works/W2798824629.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1528954144","https://openalex.org/W1677182931","https://openalex.org/W1779452081","https://openalex.org/W2039057510","https://openalex.org/W2194775991","https://openalex.org/W2281877999","https://openalex.org/W2402146185","https://openalex.org/W2516631658","https://openalex.org/W2517850878","https://openalex.org/W2520774990","https://openalex.org/W2609296554","https://openalex.org/W2890964092","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2612434969","https://openalex.org/W2802973008","https://openalex.org/W2046056978","https://openalex.org/W2951534110","https://openalex.org/W3037590244","https://openalex.org/W3010846554","https://openalex.org/W3016102464","https://openalex.org/W3016021376","https://openalex.org/W3011246070","https://openalex.org/W2900022717","https://openalex.org/W2890964092","https://openalex.org/W2916301830","https://openalex.org/W2963759317","https://openalex.org/W2972892026","https://openalex.org/W3007327651","https://openalex.org/W3020953549","https://openalex.org/W3008230514","https://openalex.org/W3015252250","https://openalex.org/W2746762607","https://openalex.org/W2049244943"],"abstract_inverted_index":{"We":[0,12,58,70,103],"investigate":[1],"deep":[2,73],"neural":[3,27],"network":[4,28],"performance":[5],"in":[6,54,127],"the":[7,20,61,68,99,106,114,128,139],"textindependent":[8],"speaker":[9,42,52,100],"recognition":[10,101],"task.":[11],"demonstrate":[13,136],"that":[14,72,105],"using":[15],"angular":[16],"softmax":[17,33],"activation":[18,34],"at":[19],"last":[21],"classification":[22,26],"layer":[23],"of":[24,30,63,138],"a":[25,31,38],"instead":[29],"simple":[32],"allows":[35],"to":[36,97,146],"train":[37],"more":[39],"generalized":[40],"discriminative":[41],"embedding":[43,56,120],"extractor.":[44,69],"Cosine":[45],"similarity":[46,109],"is":[47],"an":[48,65,119],"effective":[49],"metric":[50,110],"for":[51,67,92],"verification":[53],"this":[55],"space.":[57],"also":[59,88],"address":[60],"problem":[62],"choosing":[64],"architecture":[66],"found":[71],"networks":[74],"with":[75,144],"residual":[76],"frame":[77],"level":[78],"connections":[79],"outperform":[80],"wide":[81],"but":[82],"relatively":[83],"shallow":[84],"architectures.":[85],"This":[86],"paper":[87],"proposes":[89],"several":[90],"improvements":[91],"previous":[93],"DNN-based":[94],"extractor":[95],"systems":[96,141],"increase":[98],"accuracy.":[102],"show":[104],"discriminatively":[107],"trained":[108],"learning":[111],"approach":[112],"outperforms":[113],"standard":[115],"LDA-PLDA":[116],"method":[117],"as":[118],"backend.":[121],"The":[122],"results":[123],"obtained":[124],"on":[125],"Speakers":[126],"Wild":[129],"and":[130],"NIST":[131],"SRE":[132],"2016":[133],"evaluation":[134],"sets":[135],"robustness":[137],"proposed":[140],"when":[142],"dealing":[143],"close":[145],"real-life":[147],"conditions.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}