{"id":"https://openalex.org/W2118154032","doi":"https://doi.org/10.1186/s13636-014-0044-3","title":"Voice conversion using speaker-dependent conditional restricted Boltzmann machine","display_name":"Voice conversion using speaker-dependent conditional restricted Boltzmann machine","publication_year":2015,"publication_date":"2015-02-24","ids":{"openalex":"https://openalex.org/W2118154032","doi":"https://doi.org/10.1186/s13636-014-0044-3","mag":"2118154032"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-014-0044-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-014-0044-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0044-3","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"],"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/counter/pdf/10.1186/s13636-014-0044-3","any_repository_has_fulltext":true},"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/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada-ku, Kobe, 657-8501, Japan","Graduate School of System Informatics, Kobe University Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada-ku, Kobe, 657-8501, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Organization of Advanced Science and Technology, Kobe University, 1-1 Rokkodai, Nada-ku, Kobe, 657-8501, Japan","Organization of Advanced Science and Technology, Kobe University, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, 1-1 Rokkodai, Nada-ku, Kobe, 657-8501, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040766342","display_name":"Yasuo Ariki","orcid":"https://orcid.org/0000-0003-3473-2026"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Ariki","raw_affiliation_strings":["Organization of Advanced Science and Technology, Kobe University, 1-1 Rokkodai, Nada-ku, Kobe, 657-8501, Japan","Organization of Advanced Science and Technology, Kobe University, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, 1-1 Rokkodai, Nada-ku, Kobe, 657-8501, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041887072"],"corresponding_institution_ids":["https://openalex.org/I65837984"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.316,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89154897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8500361442565918},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.7693653106689453},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.6494331359863281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6482808589935303},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5603553056716919},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5469496846199036},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5086978077888489},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5037774443626404},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45991387963294983},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42611074447631836},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.4246440529823303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4212634861469269},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41333746910095215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500361442565918},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.7693653106689453},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.6494331359863281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6482808589935303},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5603553056716919},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5469496846199036},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5086978077888489},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5037774443626404},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45991387963294983},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42611074447631836},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.4246440529823303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212634861469269},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41333746910095215},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-014-0044-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-014-0044-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0044-3","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"],"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:da.lib.kobe-u.ac.jp:20.500.14094/90002848","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14094/90002848","pdf_url":null,"source":{"id":"https://openalex.org/S4306401924","display_name":"Kobe University Repository Kernel (Kobe University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65837984","host_organization_name":"Kobe University","host_organization_lineage":["https://openalex.org/I65837984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing\u30002015, 8-8","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/s13636-014-0044-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-014-0044-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0044-3","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"],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2118154032.pdf","grobid_xml":"https://content.openalex.org/works/W2118154032.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W17772838","https://openalex.org/W49412823","https://openalex.org/W193510348","https://openalex.org/W1517766716","https://openalex.org/W1588266896","https://openalex.org/W1813659000","https://openalex.org/W1815076433","https://openalex.org/W1950777589","https://openalex.org/W1963778986","https://openalex.org/W1965255698","https://openalex.org/W1972420736","https://openalex.org/W1993882792","https://openalex.org/W2000513720","https://openalex.org/W2017425464","https://openalex.org/W2020024436","https://openalex.org/W2022125261","https://openalex.org/W2029949252","https://openalex.org/W2030637102","https://openalex.org/W2042492924","https://openalex.org/W2100495367","https://openalex.org/W2105160541","https://openalex.org/W2108674328","https://openalex.org/W2114543868","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2131062138","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2139671364","https://openalex.org/W2146071708","https://openalex.org/W2152384560","https://openalex.org/W2156142001","https://openalex.org/W2158164339","https://openalex.org/W2158808283","https://openalex.org/W2161893161","https://openalex.org/W2165225968","https://openalex.org/W2294351487","https://openalex.org/W2401544731","https://openalex.org/W2407110532","https://openalex.org/W2577042574","https://openalex.org/W2913399920","https://openalex.org/W3031363333","https://openalex.org/W3118608800","https://openalex.org/W4244017338","https://openalex.org/W6600160826","https://openalex.org/W6600719526","https://openalex.org/W6601211009","https://openalex.org/W6601579809","https://openalex.org/W6604662147","https://openalex.org/W6606828123","https://openalex.org/W6632884021","https://openalex.org/W6725138397"],"related_works":["https://openalex.org/W4283272532","https://openalex.org/W2952018105","https://openalex.org/W2916681395","https://openalex.org/W2119341610","https://openalex.org/W2556473569","https://openalex.org/W2193475944","https://openalex.org/W4302433642","https://openalex.org/W2529583158","https://openalex.org/W2551541394","https://openalex.org/W2892911634"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,57,115,139],"voice":[4,24],"conversion":[5],"(VC)":[6],"method":[7,173],"that":[8,72],"utilizes":[9],"conditional":[10],"restricted":[11],"Boltzmann":[12],"machines":[13],"(CRBMs)":[14],"for":[15,56],"each":[16,73],"speaker":[17,61,87,104],"to":[18,42,76,122],"obtain":[19],"high-order":[20,109],"speaker-independent":[21],"spaces":[22],"where":[23,79],"features":[25,46],"are":[26,81],"converted":[27],"more":[28,86],"easily":[29],"than":[30,89],"those":[31],"in":[32,48,175],"an":[33],"original":[34,91],"acoustic":[35,92,146],"feature":[36,110],"space.":[37],"The":[38,125],"CRBM":[39,74],"is":[40,111],"expected":[41],"automatically":[43],"discover":[44],"common":[45],"lurking":[47],"time-series":[49],"data.":[50],"When":[51],"we":[52,166],"train":[53],"two":[54,129],"CRBMs":[55,130,152],"source":[58,121],"and":[59,84,131,153,187],"target":[60],"independently":[62],"using":[63,114,144],"only":[64],"speaker-dependent":[65,191],"training":[66,96],"data,":[67],"it":[68,181],"can":[69,134],"be":[70,135],"considered":[71],"tries":[75],"construct":[77],"subspaces":[78],"there":[80],"fewer":[82],"phonemes":[83,100],"relatively":[85],"individuality":[88,105],"the":[90,95,103,120,123,132,145,151,154,168],"space":[93],"because":[94],"data":[97,148],"include":[98],"various":[99],"while":[101],"keeping":[102],"unchanged.":[106],"Each":[107],"obtained":[108],"then":[112],"concatenated":[113],"neural":[116,141],"network":[117,127,142],"(NN)":[118],"from":[119],"target.":[124],"entire":[126],"(the":[128],"NN)":[133],"also":[136],"fine-tuned":[137],"as":[138],"recurrent":[140],"(RNN)":[143],"parallel":[147],"since":[149],"both":[150],"concatenating":[155],"NN":[156],"have":[157],"network-based":[158],"representation":[159],"with":[160,182],"time":[161],"dependencies.":[162],"Through":[163],"voice-conversion":[164],"experiments,":[165],"confirmed":[167],"high":[169],"performance":[170],"of":[171,177],"our":[172,188],"especially":[174],"terms":[176],"objective":[178],"evaluation,":[179],"comparing":[180],"conventional":[183],"GMM,":[184],"NN,":[185],"RNN,":[186],"previous":[189],"work,":[190],"DBN":[192],"approaches.":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}