{"id":"https://openalex.org/W2921764497","doi":"https://doi.org/10.23919/apsipa.2018.8659722","title":"Discriminative Feature Extraction Based on Sequential Variational Autoencoder for Speaker Recognition","display_name":"Discriminative Feature Extraction Based on Sequential Variational Autoencoder for Speaker Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921764497","doi":"https://doi.org/10.23919/apsipa.2018.8659722","mag":"2921764497"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659722","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101948311","display_name":"Takenori Yoshimura","orcid":"https://orcid.org/0000-0003-3964-5677"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takenori Yoshimura","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069321370","display_name":"Natsumi Koike","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Natsumi Koike","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101948311"],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":0.3384,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70971146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1742","last_page":"1746"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.998199999332428,"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/autoencoder","display_name":"Autoencoder","score":0.8983319997787476},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.890892744064331},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8297041654586792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7948223352432251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6507673263549805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.639847457408905},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.598187267780304},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5661689043045044},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5243968367576599},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5098954439163208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45670127868652344},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4404492974281311},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.43114182353019714},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4278334677219391},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31830304861068726},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2580764889717102},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09455814957618713}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8983319997787476},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.890892744064331},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8297041654586792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948223352432251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6507673263549805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.639847457408905},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.598187267780304},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5661689043045044},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5243968367576599},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5098954439163208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45670127868652344},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4404492974281311},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.43114182353019714},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4278334677219391},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31830304861068726},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2580764889717102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09455814957618713},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659722","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1959608418","https://openalex.org/W2046056978","https://openalex.org/W2091430793","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2108501770","https://openalex.org/W2134706965","https://openalex.org/W2144513243","https://openalex.org/W2150769028","https://openalex.org/W2157331557","https://openalex.org/W2165880886","https://openalex.org/W2344822617","https://openalex.org/W2395750323","https://openalex.org/W2402195372","https://openalex.org/W2406312423","https://openalex.org/W2423557781","https://openalex.org/W2515020857","https://openalex.org/W2523246573","https://openalex.org/W2612434969","https://openalex.org/W2717402182","https://openalex.org/W2747238065","https://openalex.org/W2748466034","https://openalex.org/W2748488820","https://openalex.org/W2890964092","https://openalex.org/W2913340405","https://openalex.org/W2949416428","https://openalex.org/W2962962542","https://openalex.org/W2963636093","https://openalex.org/W2963702081","https://openalex.org/W3099206234","https://openalex.org/W3127686677","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6681151457","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W4394728283","https://openalex.org/W1493875009","https://openalex.org/W4309969736","https://openalex.org/W2105231718","https://openalex.org/W4394785709"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"extended":[4],"version":[5],"of":[6,47],"the":[7,17,20,30,34,48,54,73,78,82],"variational":[8],"autoencoder":[9],"(VAE)":[10],"for":[11],"sequence":[12,63],"modeling.":[13],"In":[14],"contrast":[15],"to":[16],"original":[18],"VAE,":[19],"proposed":[21,49,79],"model":[22,32,36,50,80],"can":[23],"directly":[24],"handle":[25],"variable-length":[26],"observation":[27],"sequences.":[28],"Furthermore,":[29],"discriminative":[31],"and":[33],"generative":[35],"are":[37],"simultaneously":[38],"learned":[39],"in":[40,62],"a":[41],"unified":[42],"framework.":[43],"The":[44],"network":[45],"architecture":[46],"is":[51],"inspired":[52],"by":[53],"i-vector/PLDA":[55,84],"framework,":[56],"whose":[57],"effectiveness":[58],"has":[59],"been":[60],"proven":[61],"modeling":[64],"tasks":[65],"such":[66],"as":[67],"speaker":[68],"recognition.":[69],"Experimental":[70],"results":[71],"on":[72],"TIMIT":[74],"database":[75],"show":[76],"that":[77],"outperforms":[81],"traditional":[83],"system.":[85]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}