{"id":"https://openalex.org/W2727354829","doi":"https://doi.org/10.1186/s13636-017-0112-6","title":"Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion","display_name":"Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion","publication_year":2017,"publication_date":"2017-06-29","ids":{"openalex":"https://openalex.org/W2727354829","doi":"https://doi.org/10.1186/s13636-017-0112-6","mag":"2727354829"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-017-0112-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-017-0112-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-017-0112-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-017-0112-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["Graduate School of Information Systems, University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585, Japan","Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008413640","display_name":"Yasuhiro Minami","orcid":"https://orcid.org/0000-0003-3514-4285"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Minami","raw_affiliation_strings":["Graduate School of Information Systems, University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585, Japan","Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041887072"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":{"value":1890,"currency":"USD","value_usd":1890},"apc_paid":{"value":1890,"currency":"USD","value_usd":1890},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08082346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2017","issue":"1","first_page":null,"last_page":null},"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":0.9993000030517578,"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":0.9976000189781189,"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":0.7961937785148621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7195752859115601},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.5093291997909546},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43732336163520813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.332261323928833},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14442309737205505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961937785148621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7195752859115601},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.5093291997909546},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43732336163520813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.332261323928833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14442309737205505}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-017-0112-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-017-0112-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-017-0112-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0d5fd99fdb6c473faa1308fe95508165","is_oa":false,"landing_page_url":"https://doaj.org/article/0d5fd99fdb6c473faa1308fe95508165","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2017, Iss 1, Pp 1-10 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-017-0112-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-017-0112-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-017-0112-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2727354829.pdf","grobid_xml":"https://content.openalex.org/works/W2727354829.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W17772838","https://openalex.org/W49412823","https://openalex.org/W1517766716","https://openalex.org/W1588266896","https://openalex.org/W1596263485","https://openalex.org/W1950777589","https://openalex.org/W1963778986","https://openalex.org/W1972420736","https://openalex.org/W2009272428","https://openalex.org/W2017425464","https://openalex.org/W2020933619","https://openalex.org/W2021634140","https://openalex.org/W2022125261","https://openalex.org/W2084772916","https://openalex.org/W2105160541","https://openalex.org/W2118154032","https://openalex.org/W2120605154","https://openalex.org/W2122565151","https://openalex.org/W2123003832","https://openalex.org/W2124212365","https://openalex.org/W2126143605","https://openalex.org/W2129863563","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2169878657","https://openalex.org/W2294351487","https://openalex.org/W2400505377","https://openalex.org/W2401544731","https://openalex.org/W2404719220","https://openalex.org/W2407110532","https://openalex.org/W2577350056","https://openalex.org/W2913399920","https://openalex.org/W4244017338","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W4290792893","https://openalex.org/W2892911634","https://openalex.org/W2778699561","https://openalex.org/W2022399801","https://openalex.org/W4362513806","https://openalex.org/W3044458868","https://openalex.org/W870929296","https://openalex.org/W2883251030","https://openalex.org/W3082895349","https://openalex.org/W2152692366"],"abstract_inverted_index":{"In":[0,132,177],"this":[1],"paper,":[2],"we":[3,135],"present":[4],"a":[5,24,106,124,150,181],"voice":[6],"conversion":[7,22,179],"(VC)":[8],"method":[9],"that":[10,158,198,217],"does":[11],"not":[12,120],"use":[13,67,121],"any":[14],"parallel":[15,50,69,122],"data":[16,54,70,78],"while":[17,36],"training":[18,72,82,139,143],"the":[19,31,38,44,56,62,66,77,81,86,90,97,102,137,155,178,192,200,211,221],"model.":[20],"Voice":[21],"is":[23,34,83,93,114,127,185,195,207],"technique":[25],"where":[26],"only":[27,94],"speaker-specific":[28],"information":[29,40,161,164,194],"in":[30,71,101,108,117],"source":[32,57],"speech":[33,53,183,206],"converted":[35],"keeping":[37],"phonological":[39,160,188],"unchanged.":[41],"Most":[42],"of":[43,52,68,199],"existing":[45],"VC":[46,118],"methods":[47],"rely":[48],"on":[49,141,154],"data\u2014pairs":[51],"from":[55],"and":[58,104,162,168,189,203,227],"target":[59],"speakers":[60],"uttering":[61],"same":[63],"sentences.":[64],"However,":[65],"causes":[73],"several":[74],"problems:":[75],"(1)":[76],"used":[79,100],"for":[80],"limited":[84],"to":[85,96,119,130],"pre-defined":[87],"sentences,":[88],"(2)":[89],"trained":[91,174],"model":[92,152],"applied":[95],"speaker":[98],"pair":[99],"training,":[103],"(3)":[105],"mismatch":[107],"alignment":[109],"may":[110],"occur.":[111],"Although":[112],"it":[113],"generally":[115],"preferable":[116],"data,":[123],"non-parallel":[125,138,223],"approach":[126,219,224],"considered":[128],"difficult":[129],"learn.":[131],"our":[133,218],"approach,":[134],"realize":[136],"based":[140,153],"speaker-adaptive":[142],"(SAT).":[144],"Speech":[145],"signals":[146],"are":[147,172],"represented":[148],"using":[149,175],"probabilistic":[151],"Boltzmann":[156],"machine":[157],"defines":[159],"speaker-related":[163,190,193],"explicitly.":[165],"Speaker-independent":[166],"(SI)":[167],"speaker-dependent":[169],"(SD)":[170],"parameters":[171],"simultaneously":[173],"SAT.":[176],"stage,":[180],"given":[182],"signal":[184],"decomposed":[186],"into":[187],"information,":[191],"replaced":[196],"with":[197],"desired":[201],"speaker,":[202],"then":[204],"voice-converted":[205],"obtained":[208],"by":[209],"combining":[210],"two.":[212],"Our":[213],"experimental":[214],"results":[215],"showed":[216],"outperformed":[220],"conventional":[222],"regarding":[225],"objective":[226],"subjective":[228],"criteria.":[229]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}