{"id":"https://openalex.org/W1982641198","doi":"https://doi.org/10.1109/icassp.2014.6853856","title":"Multimodal voice conversion using non-negative matrix factorization in noisy environments","display_name":"Multimodal voice conversion using non-negative matrix factorization in noisy environments","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1982641198","doi":"https://doi.org/10.1109/icassp.2014.6853856","mag":"1982641198"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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, Kobe, Japan","Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, 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, Kobe, Japan","Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Grad. Sch. of Syst. Inf., Kobe Univ., 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, Kobe, Japan","Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Grad. Sch. of Syst. Inf., Kobe Univ., 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, Kobe, Japan","Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, 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":null,"apc_paid":null,"fwci":3.6811,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93426301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"1542","last_page":"1546"},"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":0.9998000264167786,"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":0.9986000061035156,"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":0.8689658641815186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8015693426132202},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.736239492893219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6808852553367615},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5588934421539307},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5124897956848145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4986574649810791},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.49148285388946533},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4626544117927551},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45222926139831543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43958595395088196},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2734133303165436},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20523971319198608},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06619971990585327}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8689658641815186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015693426132202},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.736239492893219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6808852553367615},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5588934421539307},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5124897956848145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4986574649810791},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.49148285388946533},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4626544117927551},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45222926139831543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43958595395088196},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2734133303165436},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20523971319198608},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06619971990585327},{"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/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":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":33,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W49412823","https://openalex.org/W71477782","https://openalex.org/W185399533","https://openalex.org/W1566744681","https://openalex.org/W1588266896","https://openalex.org/W1599408644","https://openalex.org/W1963778986","https://openalex.org/W1965255698","https://openalex.org/W2011378162","https://openalex.org/W2017425464","https://openalex.org/W2022125261","https://openalex.org/W2049686551","https://openalex.org/W2059520982","https://openalex.org/W2077801020","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/W2156142001","https://openalex.org/W2407110532","https://openalex.org/W2577350056","https://openalex.org/W3143596294","https://openalex.org/W6602007935","https://openalex.org/W6633899882","https://openalex.org/W6635216677","https://openalex.org/W6680012447","https://openalex.org/W6732045268"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2900450731"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,85,115,135],"multimodal":[4,86],"voice":[5],"conversion":[6],"(VC)":[7],"method":[8,125],"for":[9],"noisy":[10],"environments.":[11],"In":[12,80],"our":[13,94],"previous":[14,116],"NMF-based":[15,95,118],"VC":[16,87,96,110,119],"method,":[17],"source":[18,38,44,50,78,105],"exemplars":[19,22,53,71],"and":[20,39,59,72],"target":[21,40,70],"are":[23,34],"extracted":[24],"from":[25,55,68],"parallel":[26],"training":[27],"data,":[28],"in":[29,93],"which":[30],"the":[31,37,56,63,69,73,77,90,100,107],"same":[32],"texts":[33],"uttered":[35],"by":[36,128],"speakers.":[41],"The":[42,121],"input":[43,57],"signal":[45],"is":[46,66,111],"then":[47],"decomposed":[48],"into":[49],"exemplars,":[51],"noise":[52,91],"obtained":[54],"signal,":[58],"their":[60],"weights.":[61],"Then,":[62],"converted":[64],"speech":[65],"constructed":[67],"weights":[74],"related":[75],"to":[76,114],"exemplars.":[79],"this":[81,124],"paper,":[82],"we":[83],"propose":[84],"that":[88,133],"improves":[89],"robustness":[92],"method.":[97,120,141],"By":[98],"using":[99],"joint":[101],"audio-visual":[102],"features":[103],"as":[104],"features,":[106],"performance":[108],"of":[109,123,134],"improved":[112],"compared":[113],"audio-input":[117],"effectiveness":[122,131],"was":[126],"confirmed":[127],"comparing":[129],"its":[130],"with":[132],"conventional":[136],"Gaussian":[137],"Mixture":[138],"Model":[139],"(GMM)-based":[140]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}