{"id":"https://openalex.org/W2147872185","doi":"https://doi.org/10.1186/s13636-015-0067-4","title":"Multimodal voice conversion based on non-negative matrix factorization","display_name":"Multimodal voice conversion based on non-negative matrix factorization","publication_year":2015,"publication_date":"2015-09-03","ids":{"openalex":"https://openalex.org/W2147872185","doi":"https://doi.org/10.1186/s13636-015-0067-4","mag":"2147872185"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-015-0067-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0067-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0067-4","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/s13636-015-0067-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054450140","display_name":"Kenta Masaka","orcid":null},"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":"Kenta Masaka","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Kobe, 657-8501, Nada-ku, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Kobe, 657-8501, Nada-ku, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011355805","display_name":"Ryo Aihara","orcid":"https://orcid.org/0009-0006-6492-3754"},"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":"Ryo Aihara","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Kobe, 657-8501, Nada-ku, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Kobe, 657-8501, Nada-ku, 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-kuKobe, 657-8501, Japan"],"affiliations":[{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, 1-1 Rokkodai, Nada-kuKobe, 657-8501, 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-kuKobe, 657-8501, Japan"],"affiliations":[{"raw_affiliation_string":"Organization of Advanced Science and Technology, Kobe University, 1-1 Rokkodai, Nada-kuKobe, 657-8501, Japan","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054450140"],"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":0.579,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67642669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8718692660331726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7923799753189087},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6660622954368591},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6658017635345459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6619700193405151},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5531050562858582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46022161841392517},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43275386095046997},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4229370355606079},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4172712564468384},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4159984886646271},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2593042254447937},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23006677627563477}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8718692660331726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923799753189087},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6660622954368591},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6658017635345459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6619700193405151},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5531050562858582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46022161841392517},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43275386095046997},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4229370355606079},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4172712564468384},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4159984886646271},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2593042254447937},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23006677627563477},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-015-0067-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0067-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0067-4","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:20.500.14094/90002951","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14094/90002951","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, 24-24","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/s13636-015-0067-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0067-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0067-4","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147872185.pdf","grobid_xml":"https://content.openalex.org/works/W2147872185.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W49412823","https://openalex.org/W185399533","https://openalex.org/W1566744681","https://openalex.org/W1588266896","https://openalex.org/W1599408644","https://openalex.org/W1963778986","https://openalex.org/W1965912016","https://openalex.org/W1977362459","https://openalex.org/W1982641198","https://openalex.org/W2011378162","https://openalex.org/W2017425464","https://openalex.org/W2022125261","https://openalex.org/W2059520982","https://openalex.org/W2062507334","https://openalex.org/W2077801020","https://openalex.org/W2078517841","https://openalex.org/W2078722660","https://openalex.org/W2102863932","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2124174353","https://openalex.org/W2135029798","https://openalex.org/W2141520175","https://openalex.org/W2150415460","https://openalex.org/W2152826865","https://openalex.org/W2156142001","https://openalex.org/W2401967023","https://openalex.org/W2407110532","https://openalex.org/W4247403446"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W2037504162","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291","https://openalex.org/W2900450731"],"abstract_inverted_index":{"A":[0],"multimodal":[1,81],"voice":[2],"conversion":[3],"(VC)":[4],"method":[5,141,155],"for":[6],"noisy":[7],"environments":[8],"is":[9,47,62,124,142],"proposed.":[10],"In":[11,76],"our":[12,89],"previous":[13,131],"non-negative":[14],"matrix":[15],"factorization":[16],"(NMF)-based":[17],"VC":[18,82,91,122,134],"method,":[19],"source":[20,39,45,51,74,120],"and":[21,40,55,68,101,104,156],"target":[22,41,66],"exemplars":[23,67],"are":[24,35],"extracted":[25],"from":[26,64],"parallel":[27],"training":[28],"data,":[29],"in":[30],"which":[31],"the":[32,38,59,65,69,73,85,96,115,139],"same":[33],"texts":[34],"uttered":[36],"by":[37,144],"speakers.":[42],"The":[43,136],"input":[44],"signal":[46],"then":[48],"decomposed":[49],"into":[50],"exemplars,":[52,54],"noise":[53,86],"their":[56],"weights.":[57],"Then,":[58],"converted":[60],"speech":[61],"constructed":[63],"weights":[70],"related":[71],"to":[72,110],"exemplars.":[75,113],"this":[77],"study,":[78],"we":[79,94],"propose":[80],"that":[83,128,149],"improves":[84],"robustness":[87],"of":[88,129,138,150],"NMF-based":[90,154],"method.":[92,135,161],"Furthermore,":[93],"introduce":[95],"combination":[97],"weight":[98],"between":[99],"audio":[100],"visual":[102],"features":[103,118],"formulate":[105],"a":[106,130,151,157],"new":[107],"cost":[108],"function":[109],"estimate":[111],"audio-visual":[112,117],"Using":[114],"joint":[116],"as":[119],"features,":[121],"performance":[123],"improved":[125],"compared":[126],"with":[127,148],"audio-input":[132,153],"exemplar-based":[133],"effectiveness":[137,147],"proposed":[140],"confirmed":[143],"comparing":[145],"its":[146],"conventional":[152],"Gaussian":[158],"mixture":[159],"model-based":[160]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
