{"id":"https://openalex.org/W3096649599","doi":"https://doi.org/10.21437/interspeech.2020-2542","title":"Neural Discriminant Analysis for Deep Speaker Embedding","display_name":"Neural Discriminant Analysis for Deep Speaker Embedding","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096649599","doi":"https://doi.org/10.21437/interspeech.2020-2542","mag":"3096649599"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2542","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100391494"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3251","last_page":"3255"},"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":0.9997000098228455,"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":0.9950000047683716,"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":0.6682765483856201},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6621533036231995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5936490893363953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5751916766166687},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.4945344626903534},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47177720069885254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46812453866004944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43705466389656067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682765483856201},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6621533036231995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5936490893363953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5751916766166687},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.4945344626903534},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47177720069885254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46812453866004944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43705466389656067}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2542","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1494871301","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1526075880","https://openalex.org/W1583912456","https://openalex.org/W1589137271","https://openalex.org/W2046056978","https://openalex.org/W2104067967","https://openalex.org/W2107638917","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2395750323","https://openalex.org/W2406312423","https://openalex.org/W2516764878","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962832278","https://openalex.org/W2963371159","https://openalex.org/W2963382494","https://openalex.org/W2972956697","https://openalex.org/W3015598461","https://openalex.org/W3111759753","https://openalex.org/W3150807214","https://openalex.org/W4297798428"],"related_works":["https://openalex.org/W2350751952","https://openalex.org/W1999647744","https://openalex.org/W2362114017","https://openalex.org/W3147024994","https://openalex.org/W2063246903","https://openalex.org/W2374055396","https://openalex.org/W1978302214","https://openalex.org/W2021817983","https://openalex.org/W3008559849","https://openalex.org/W2371177901"],"abstract_inverted_index":{"Probabilistic":[0],"Linear":[1],"Discriminant":[2,44],"Analysis":[3,45],"(PLDA)":[4],"is":[5,28],"a":[6,35,56,60,82],"popular":[7],"tool":[8],"in":[9,73],"open-set":[10],"classification/verification":[11],"tasks.However,":[12],"the":[13,26,65,74,87,107,111],"Gaussian":[14,67],"assumption":[15],"underlying":[16],"PLDA":[17,40],"prevents":[18],"it":[19],"from":[20],"being":[21],"applied":[22],"to":[23,54,59],"situations":[24],"where":[25,86],"data":[27],"clearly":[29],"non-Gaussian.In":[30],"this":[31,78],"paper,":[32],"we":[33],"present":[34],"novel":[36],"nonlinear":[37],"version":[38],"of":[39,110],"named":[41],"as":[42],"Neural":[43],"(NDA).This":[46],"model":[47,68,80],"employs":[48],"an":[49],"invertible":[50],"deep":[51,88],"neural":[52],"network":[53],"transform":[55],"complex":[57],"distribution":[58],"simple":[61],"Gaussian,":[62],"so":[63],"that":[64,100],"linear":[66],"can":[69],"be":[70],"readily":[71],"established":[72],"transformed":[75],"space.We":[76],"tested":[77],"NDA":[79,101],"on":[81,96],"speaker":[83,89],"recognition":[84],"task":[85],"vectors":[90],"(x-vectors)":[91],"are":[92],"presumably":[93],"non-Gaussian.Experimental":[94],"results":[95],"two":[97],"datasets":[98],"demonstrate":[99],"consistently":[102],"outperforms":[103],"PLDA,":[104],"by":[105],"handling":[106],"non-Gaussian":[108],"distributions":[109],"x-vectors.":[112]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}