{"id":"https://openalex.org/W2740504963","doi":"https://doi.org/10.1186/s13636-017-0116-2","title":"Emotional voice conversion using neural networks with arbitrary scales F0 based on wavelet transform","display_name":"Emotional voice conversion using neural networks with arbitrary scales F0 based on wavelet transform","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2740504963","doi":"https://doi.org/10.1186/s13636-017-0116-2","mag":"2740504963"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-017-0116-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-017-0116-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-017-0116-2","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/s13636-017-0116-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077713342","display_name":"Zhaojie Luo","orcid":"https://orcid.org/0000-0002-4173-6319"},"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":"Zhaojie Luo","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, Japan","Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4173-6319","affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, 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/A5100627380","display_name":"Jinhui Chen","orcid":"https://orcid.org/0000-0002-3701-9026"},"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":"Jinhui Chen","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, Japan","Graduate School of System Informatics, Kobe University, Kobe, Japan","RIEB, Kobe University, 2-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, Japan","RIEB, Kobe University, Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, 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"]},{"raw_affiliation_string":"RIEB, Kobe University, 2-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"RIEB, 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":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, Japan","Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, 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":"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":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, Japan","Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada, Kobe, Hyogo, Kobe, 657-8501, Hyogo, 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65837984"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":3.8478,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94549831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.9951000213623047,"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/speech-recognition","display_name":"Speech recognition","score":0.7002480030059814},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6235488057136536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6111528277397156},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5832933187484741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5410436987876892},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5397108793258667},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5148407816886902},{"id":"https://openalex.org/keywords/continuous-wavelet-transform","display_name":"Continuous wavelet transform","score":0.4932553172111511},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4275748133659363},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4196377396583557},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.41843974590301514},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.3374446630477905},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.19724246859550476}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7002480030059814},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6235488057136536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6111528277397156},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5832933187484741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410436987876892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5397108793258667},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5148407816886902},{"id":"https://openalex.org/C95722684","wikidata":"https://www.wikidata.org/wiki/Q2622756","display_name":"Continuous wavelet transform","level":5,"score":0.4932553172111511},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4275748133659363},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4196377396583557},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.41843974590301514},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.3374446630477905},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19724246859550476}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13636-017-0116-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-017-0116-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-017-0116-2","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:infocom.co.jp:G0000003oai:90004229","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407053249","display_name":"Infolib","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:da.lib.kobe-u.ac.jp:20.500.14094/90004229","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14094/90004229","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\u30002017, 18-18","raw_type":"journal article"},{"id":"pmh:oai:doaj.org/article:b689c65684ea42de938fc2a188381a71","is_oa":true,"landing_page_url":"https://doaj.org/article/b689c65684ea42de938fc2a188381a71","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2017, Iss 1, Pp 1-13 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-017-0116-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-017-0116-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-017-0116-2","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8819468294","display_name":"Research on communication support technology for persons with articulation disorders using multiple modalities","funder_award_id":"17H01995","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740504963.pdf","grobid_xml":"https://content.openalex.org/works/W2740504963.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W31448757","https://openalex.org/W155193863","https://openalex.org/W228380312","https://openalex.org/W847441270","https://openalex.org/W1540083112","https://openalex.org/W1588037970","https://openalex.org/W2017425464","https://openalex.org/W2089624917","https://openalex.org/W2093450784","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123771434","https://openalex.org/W2126143605","https://openalex.org/W2137639365","https://openalex.org/W2152205330","https://openalex.org/W2164241094","https://openalex.org/W2185573909","https://openalex.org/W2251981003","https://openalex.org/W2294351487","https://openalex.org/W2399915284","https://openalex.org/W2511640485","https://openalex.org/W2517513811","https://openalex.org/W2526785520","https://openalex.org/W2537786327","https://openalex.org/W6606511648","https://openalex.org/W6606828123","https://openalex.org/W6638407004"],"related_works":["https://openalex.org/W2030316446","https://openalex.org/W2085792030","https://openalex.org/W1588899229","https://openalex.org/W2023142747","https://openalex.org/W2172291505","https://openalex.org/W2063036707","https://openalex.org/W2037009764","https://openalex.org/W2501033992","https://openalex.org/W2377605153","https://openalex.org/W2094847008"],"abstract_inverted_index":{"An":[0],"artificial":[1],"neural":[2,17],"network":[3],"is":[4,46,58],"an":[5,66,96,175],"important":[6],"model":[7],"for":[8,49,65,104,174],"training":[9],"features":[10,125],"of":[11,42,63,95,126,188],"voice":[12,55,68,177],"conversion":[13],"(VC)":[14],"tasks.":[15],"Typically,":[16],"networks":[18,149],"(NNs)":[19],"are":[20],"very":[21],"effective":[22],"in":[23,72,107,186],"processing":[24],"nonlinear":[25],"features,":[26],"such":[27],"as":[28,179,181],"Mel":[29],"Cepstral":[30],"Coefficients":[31],"(MCC),":[32],"which":[33,98,130],"represent":[34,132],"the":[35,60,78,115,143,153,164,169,172],"spectrum":[36,170],"features.":[37,159],"However,":[38],"a":[39],"simple":[40],"representation":[41],"fundamental":[43],"frequency":[44],"(F0)":[45],"not":[47],"enough":[48],"NNs":[50,103,154],"to":[51,83,121,139,151],"deal":[52],"with":[53],"emotional":[54,67,108,176,189],"VC.":[56,109,190],"This":[57],"because":[59],"time":[61],"sequence":[62],"F0":[64,85,124,173],"changes":[69],"drastically.":[70],"Therefore,":[71],"our":[73],"previous":[74],"method,":[75],"we":[76,113],"used":[77],"continuous":[79],"wavelet":[80],"transform":[81],"(CWT)":[82],"decompose":[84],"into":[86],"30":[87],"discrete":[88],"scales,":[89,129],"each":[90],"separated":[91],"by":[92,102],"one":[93],"third":[94],"octave,":[97],"can":[99,131,167],"be":[100],"trained":[101],"prosody":[105],"modeling":[106],"In":[110],"this":[111],"study,":[112],"propose":[114],"arbitrary":[116],"scales":[117],"CWT":[118],"(AS-CWT)":[119],"method":[120,145,166],"systematically":[122],"capture":[123],"different":[127,133],"temporal":[128],"prosodic":[134],"levels":[135],"ranging":[136],"from":[137],"micro-prosody":[138],"sentence":[140],"levels.":[141],"Meanwhile,":[142],"proposed":[144,165],"uses":[146],"deep":[147],"belief":[148],"(DBNs)":[150],"pre-train":[152],"that":[155],"then":[156],"convert":[157],"spectral":[158],"By":[160],"utilizing":[161],"these":[162],"approaches,":[163],"change":[168],"and":[171],"simultaneously":[178],"well":[180],"outperform":[182],"other":[183],"state-of-the-art":[184],"methods":[185],"terms":[187]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}