{"id":"https://openalex.org/W2922475298","doi":"https://doi.org/10.23919/apsipa.2018.8659675","title":"Data augmentation with moment-matching networks for i-vector based speaker verification","display_name":"Data augmentation with moment-matching networks for i-vector based speaker verification","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922475298","doi":"https://doi.org/10.23919/apsipa.2018.8659675","mag":"2922475298"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659675","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659675","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/A5067910092","display_name":"Sayaka Shiota","orcid":"https://orcid.org/0000-0002-2364-068X"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sayaka Shiota","raw_affiliation_strings":["Faculty of System Design, Tokyo Metropolitan University, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of System Design, Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067714865","display_name":"Tomoko Matsui","orcid":"https://orcid.org/0000-0003-3201-6106"},"institutions":[{"id":"https://openalex.org/I4210134673","display_name":"The Institute of Statistical Mathematics","ror":"https://ror.org/03jcejr58","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210134673","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoko Matsui","raw_affiliation_strings":["The Institue of Statistical and Mathematics, Japan"],"affiliations":[{"raw_affiliation_string":"The Institue of Statistical and Mathematics, Japan","institution_ids":["https://openalex.org/I4210134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067910092"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19365306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"349"},"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":0.9979000091552734,"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":0.9962000250816345,"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/support-vector-machine","display_name":"Support vector machine","score":0.8236740827560425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923430562019348},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6672042012214661},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5937581062316895},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.590099573135376},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5828776359558105},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47521787881851196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4630261957645416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4584583342075348},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35561951994895935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17450368404388428},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07840001583099365}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.8236740827560425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923430562019348},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6672042012214661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5937581062316895},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.590099573135376},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5828776359558105},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47521787881851196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4630261957645416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4584583342075348},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35561951994895935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17450368404388428},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07840001583099365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659675","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659675","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":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1487641199","https://openalex.org/W1527535554","https://openalex.org/W1916834241","https://openalex.org/W2005522781","https://openalex.org/W2026358225","https://openalex.org/W2046056978","https://openalex.org/W2099471712","https://openalex.org/W2146502635","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2402156731","https://openalex.org/W2406312423","https://openalex.org/W2407374891","https://openalex.org/W2428952132","https://openalex.org/W2519091744","https://openalex.org/W2524591323","https://openalex.org/W2577946330","https://openalex.org/W2578392894","https://openalex.org/W2607404225","https://openalex.org/W2746762848","https://openalex.org/W2747249235","https://openalex.org/W2770173563","https://openalex.org/W2890964092","https://openalex.org/W2962916039","https://openalex.org/W2963609956","https://openalex.org/W4320013936","https://openalex.org/W6629354409","https://openalex.org/W6640010188","https://openalex.org/W6681435938","https://openalex.org/W6713239009","https://openalex.org/W6713727690","https://openalex.org/W6714259624","https://openalex.org/W6718237598","https://openalex.org/W6732248266"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205","https://openalex.org/W2150532155"],"abstract_inverted_index":{"This":[0],"paper":[1,50],"proposes":[2],"an":[3],"i-vector":[4,59],"generation":[5],"scheme":[6],"with":[7,61,68,110],"conditional":[8],"generative":[9],"moment-matching":[10],"networks":[11],"(MMNs)":[12],"for":[13,21,44,87],"speaker":[14,24,65],"verification.":[15],"In":[16],"this":[17,49],"scheme,":[18],"multiple":[19],"i-vectors":[20,37,84,109],"each":[22,45],"enrollment":[23,46,95],"are":[25,38,73,85],"randomly":[26,35],"generated":[27,36,83,108],"from":[28],"trained":[29],"MMNs":[30],"and":[31,116],"noise":[32],"distributions.":[33],"The":[34,75],"assumed":[39],"to":[40,53],"represent":[41],"diverse":[42],"variations":[43],"speaker.":[47],"Since":[48],"is":[51],"aim":[52],"provide":[54],"new":[55],"possibility":[56],"of":[57,77,89,94,106,112],"the":[58,82,90,98,104,107,113],"augmentation":[60],"MMNs,":[62],"i-vector-based":[63],"preliminary":[64],"verification":[66],"evaluation":[67],"support":[69],"vector":[70],"machine":[71],"(SVM)":[72],"performed.":[74],"results":[76],"SVM":[78,92],"classification":[79],"show":[80],"that":[81],"contributed":[86],"estimation":[88],"accurate":[91],"classifiers":[93],"speakers.":[96],"From":[97],"experimental":[99],"results,":[100],"we":[101],"also":[102],"compare":[103],"distributions":[105],"those":[111],"original":[114],"ones":[115],"discuss":[117],"them.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}