{"id":"https://openalex.org/W3004720752","doi":"https://doi.org/10.21437/odyssey.2020-29","title":"NPLDA: A Deep Neural PLDA Model for Speaker Verification","display_name":"NPLDA: A Deep Neural PLDA Model for Speaker Verification","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3004720752","doi":"https://doi.org/10.21437/odyssey.2020-29","mag":"3004720752"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-29","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-29","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.03562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shreyas Ramoji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shreyas Ramoji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Prashant Krishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prashant Krishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Sriram Ganapathy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.979,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92725537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"202","last_page":"209"},"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":0.9983999729156494,"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":0.9972000122070312,"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/speaker-verification","display_name":"Speaker verification","score":0.7454000115394592},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.598800003528595},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5116000175476074},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4999000132083893},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47450000047683716},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45559999346733093},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4526999890804291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680000066757202},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7454000115394592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6323000192642212},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.598800003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429999828338623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4999000132083893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2020-29","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-29","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"},{"id":"pmh:oai:arXiv.org:2002.03562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03562","pdf_url":"https://arxiv.org/pdf/2002.03562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.03562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03562","pdf_url":"https://arxiv.org/pdf/2002.03562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,43,73,89,106],"state-of-art":[1,148],"approach":[2,36],"for":[3,37,92],"speaker":[4,41,107,118,151],"verification":[5,71,152],"consists":[6],"of":[7,47,63,99],"a":[8,16,33,55,70],"neural":[9,34,78],"network":[10,35],"based":[11,150],"embedding":[12],"extractor":[13],"along":[14],"with":[15],"backend":[17,38],"generative":[18,49,85],"model":[19,51,87,95,113,137],"such":[20],"as":[21,54,77,125,127],"the":[22,48,60,64,84,93,100,111,117,122,128,135,140,147],"Probabilistic":[23],"Linear":[24],"Discriminant":[25],"Analysis":[26],"(PLDA).":[27],"In":[28,132],"this":[29],"work,":[30],"we":[31],"propose":[32],"modeling":[39],"in":[40,121],"recognition.":[42],"likelihood":[44],"ratio":[45],"score":[46,65],"PLDA":[50,79,86,149],"is":[52,81,96],"posed":[53],"discriminative":[56],"similarity":[57],"function":[58,66,91,104,143],"and":[59],"learnable":[61],"parameters":[62],"are":[67,114],"optimized":[68,138],"using":[69,83,110,139],"cost.":[72],"proposed":[74,141],"model,":[75],"termed":[76],"(NPLDA),":[80],"initialized":[82],"parameters.":[88],"loss":[90,142],"NPLDA":[94,112,136],"an":[97],"approximation":[98],"minimum":[101],"detection":[102],"cost":[103],"(DCF).":[105],"recognition":[108],"experiments":[109],"performed":[115],"on":[116],"verificiation":[119],"task":[120],"VOiCES":[123],"datasets":[124],"well":[126],"SITW":[129],"challenge":[130],"dataset.":[131],"these":[133],"experiments,":[134],"improves":[144],"significantly":[145],"over":[146],"system.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2020-02-14T00:00:00"}