{"id":"https://openalex.org/W2023661015","doi":"https://doi.org/10.1109/mlsp.2013.6661965","title":"Voice conversion for arbitrary speakers using articulatory-movement to vocal-tract parameter mapping","display_name":"Voice conversion for arbitrary speakers using articulatory-movement to vocal-tract parameter mapping","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2023661015","doi":"https://doi.org/10.1109/mlsp.2013.6661965","mag":"2023661015"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2013.6661965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2013.6661965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5059279939","display_name":"Narpendyah W. Ariwardhani","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Narpendyah W. Ariwardhani","raw_affiliation_strings":["Graduate School of Engineering, Toyohashi University of Technology, Japan","Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112017946","display_name":"Yurie Iribe","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yurie Iribe","raw_affiliation_strings":["Graduate School of Engineering, Toyohashi University of Technology, Japan","Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108640197","display_name":"Kouichi Katsurada","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouichi Katsurada","raw_affiliation_strings":["Graduate School of Engineering, Toyohashi University of Technology, Japan","Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109901270","display_name":"Tsuneo Nitta","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuneo Nitta","raw_affiliation_strings":["Graduate School of Engineering, Toyohashi University of Technology, Japan","Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Grad. Sch. of Eng., Toyohashi Univ. of Technol., Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136259955"],"apc_list":null,"apc_paid":null,"fwci":2.4717,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9018091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9987999796867371,"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":0.9961000084877014,"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/vocal-tract","display_name":"Vocal tract","score":0.8255921602249146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7756264209747314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7681667804718018},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.568087100982666},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5107667446136475},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.500978946685791},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4996514320373535},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4359714090824127},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4129739999771118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34686920046806335},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1478586494922638}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8255921602249146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7756264209747314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681667804718018},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.568087100982666},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5107667446136475},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.500978946685791},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4996514320373535},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4359714090824127},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4129739999771118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34686920046806335},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1478586494922638},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2013.6661965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2013.6661965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W46785905","https://openalex.org/W94226176","https://openalex.org/W152891837","https://openalex.org/W1526513105","https://openalex.org/W1963778986","https://openalex.org/W1994477412","https://openalex.org/W2007023536","https://openalex.org/W2105698384","https://openalex.org/W2110584444","https://openalex.org/W2114543868","https://openalex.org/W2120605154","https://openalex.org/W2131962962","https://openalex.org/W2150658333","https://openalex.org/W2155028248","https://openalex.org/W6601897821","https://openalex.org/W6606230598"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2740630172"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"voice":[5,35,49,74,90,99,116,134],"conversion":[6,75,91,100,117],"based":[7],"on":[8],"articulatory-movement":[9],"(AM)":[10],"to":[11,24,27,30,36,71,108],"vocal":[12],"tract":[13],"parameter":[14],"(VTP)":[15],"mapping.":[16],"An":[17],"artificial":[18],"neural":[19],"network":[20],"(ANN)":[21],"is":[22,44,82,135],"applied":[23],"map":[25],"AM":[26],"VTP":[28],"and":[29,77,105,137],"convert":[31],"the":[32,37,73,110,120,132,142],"source":[33,59,68,79],"speaker's":[34,39],"target":[38,143],"voice.":[40],"The":[41,96,127],"proposed":[42,114],"system":[43],"not":[45],"only":[46,83],"text":[47],"independent":[48],"conversion,":[50],"but":[51],"can":[52],"also":[53,94],"be":[54],"used":[55],"for":[56],"an":[57],"arbitrary":[58],"speaker.":[60,144],"This":[61],"means":[62],"that":[63,131],"our":[64,113],"approach":[65],"requires":[66],"no":[67],"speaker":[69,80,139],"data":[70,81],"build":[72],"model":[76,124],"hence":[78],"required":[84],"during":[85],"testing":[86],"phase.":[87],"Preliminary":[88],"cross-lingual":[89],"experiments":[92],"are":[93],"conducted.":[95],"results":[97,129],"of":[98,112,141],"were":[101],"evaluated":[102],"using":[103],"subjective":[104],"objective":[106],"measures":[107],"compare":[109],"performance":[111],"ANN-based":[115],"(VC)":[118],"with":[119],"state-of-the-art":[121],"Gaussian":[122],"mixture":[123],"(GMM)-based":[125],"VC.":[126],"experimental":[128],"show":[130],"converted":[133],"intelligible":[136],"has":[138],"individuality":[140]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}