{"id":"https://openalex.org/W2407314578","doi":"https://doi.org/10.1109/icassp.2016.7472716","title":"Divergence estimation based on deep neural networks and its use for language identification","display_name":"Divergence estimation based on deep neural networks and its use for language identification","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407314578","doi":"https://doi.org/10.1109/icassp.2016.7472716","mag":"2407314578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089333825","display_name":"Congying Zhang","orcid":"https://orcid.org/0000-0002-5723-9851"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Congying Zhang","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"5435","last_page":"5439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.9941999912261963,"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/divergence","display_name":"Divergence (linguistics)","score":0.875905454158783},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7405459880828857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5676814913749695},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5619147419929504},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5304253101348877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141337513923645},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.48198050260543823},{"id":"https://openalex.org/keywords/density-estimation","display_name":"Density estimation","score":0.4816645383834839},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.47666528820991516},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4761757254600525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46236804127693176},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.45219430327415466},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4395481050014496},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.42489010095596313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37095701694488525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32112935185432434},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1851237416267395},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.18464097380638123}],"concepts":[{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.875905454158783},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7405459880828857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5676814913749695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5619147419929504},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5304253101348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141337513923645},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.48198050260543823},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.4816645383834839},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.47666528820991516},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4761757254600525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46236804127693176},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.45219430327415466},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4395481050014496},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.42489010095596313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37095701694488525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32112935185432434},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1851237416267395},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.18464097380638123},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1993882792","https://openalex.org/W2033178790","https://openalex.org/W2045317385","https://openalex.org/W2100966557","https://openalex.org/W2136922672","https://openalex.org/W2149338142","https://openalex.org/W2151381157","https://openalex.org/W2156172072","https://openalex.org/W2164805947","https://openalex.org/W2402040300","https://openalex.org/W2407126428","https://openalex.org/W2940671201","https://openalex.org/W6684793055","https://openalex.org/W6712847557","https://openalex.org/W6762265944"],"related_works":["https://openalex.org/W63219142","https://openalex.org/W1570464650","https://openalex.org/W1528820368","https://openalex.org/W2187148935","https://openalex.org/W1569550976","https://openalex.org/W2543710962","https://openalex.org/W2043285515","https://openalex.org/W2105808439","https://openalex.org/W1937731701","https://openalex.org/W2061808167"],"abstract_inverted_index":{"In":[0,68,88],"this":[1,143,163],"paper,":[2],"we":[3],"propose":[4],"a":[5,15,33,47,52,103,149,156,177],"method":[6,152],"to":[7,98,123,137,165,175,197],"estimate":[8],"statistical":[9,27,77],"divergence":[10,28,65,78,92,129],"between":[11,55,93],"probability":[12,37],"distributions":[13,95],"by":[14,72,81,193],"DNN-based":[16],"discriminative":[17,85],"approach":[18,158,164,185,200],"and":[19,59,136,155],"its":[20,60],"use":[21],"for":[22,106,115,153,159],"language":[23,166,191],"identification":[24,167,192],"tasks.":[25],"Since":[26],"is":[29,79,96,117],"generally":[30],"defined":[31],"as":[32,84],"functional":[34],"of":[35,112,127,190],"two":[36,94,145],"density":[38,41],"functions,":[39],"these":[40,107],"functions":[42],"are":[43,147,173],"usually":[44],"represented":[45],"in":[46],"parametric":[48],"form.":[49],"Then,":[50],"if":[51],"mismatch":[53],"exists":[54],"the":[56,63,76,91,110,125,128,133,170,188,198],"assumed":[57],"distribution":[58],"true":[61],"one,":[62],"obtained":[64,171],"becomes":[66,121],"erroneous.":[67],"our":[69,89,184],"proposed":[70],"method,":[71,90],"using":[73,82],"Bayes'":[74],"theorem,":[75],"estimated":[80,100],"DNN":[83,154],"estimation":[86,116],"model.":[87],"able":[97],"be":[99],"without":[101],"assuming":[102],"specific":[104],"form":[105],"distributions.":[108],"When":[109],"amount":[111],"data":[113],"available":[114],"small,":[118],"however,":[119],"it":[120],"intractable":[122],"calculate":[124],"integral":[126],"function":[130],"over":[131],"all":[132],"feature":[134],"space":[135],"train":[138],"neural":[139],"networks.":[140],"To":[141],"mitigate":[142],"problem,":[144],"solutions":[146],"introduced;":[148],"model":[150],"adaptation":[151],"sampling":[157],"integration.":[160],"We":[161],"apply":[162],"tasks,":[168],"where":[169],"divergences":[172],"used":[174],"extract":[176],"speech":[178],"structure.":[179],"Experimental":[180],"results":[181],"show":[182],"that":[183],"can":[186],"improve":[187],"performance":[189],"10.85%":[194],"relative":[195],"compared":[196],"conventional":[199],"based":[201],"on":[202],"i-vector.":[203]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}