{"id":"https://openalex.org/W4386902717","doi":"https://doi.org/10.1109/taslp.2023.3313426","title":"Noisy-to-Noisy Voice Conversion Under Variations of Noisy Condition","display_name":"Noisy-to-Noisy Voice Conversion Under Variations of Noisy Condition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386902717","doi":"https://doi.org/10.1109/taslp.2023.3313426"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313426","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313426","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10256118.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10256118.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chao Xie","orcid":"https://orcid.org/0000-0002-6237-9816"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chao Xie","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6237-9816","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.8699,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73333333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3871","last_page":"3882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9954000115394592,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9818999767303467,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/noise","display_name":"Noise (video)","score":0.738949716091156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7335758209228516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6972291469573975},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5950111746788025},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5414085984230042},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5283435583114624},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5261484980583191},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5102338790893555},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.49249252676963806},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.47823256254196167},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3347882032394409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31832122802734375},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1003744900226593},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07205891609191895},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05647537112236023}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.738949716091156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335758209228516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6972291469573975},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5950111746788025},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5414085984230042},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5283435583114624},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5261484980583191},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5102338790893555},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.49249252676963806},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.47823256254196167},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3347882032394409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31832122802734375},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1003744900226593},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07205891609191895},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05647537112236023},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/taslp.2023.3313426","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313426","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10256118.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3313426","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313426","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10256118.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386902717.pdf","grobid_xml":"https://content.openalex.org/works/W4386902717.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W2013996527","https://openalex.org/W2017425464","https://openalex.org/W2052666245","https://openalex.org/W2107860279","https://openalex.org/W2156142001","https://openalex.org/W2532494225","https://openalex.org/W2577350056","https://openalex.org/W2603567530","https://openalex.org/W2804998325","https://openalex.org/W2899877258","https://openalex.org/W2902070858","https://openalex.org/W2907262790","https://openalex.org/W2937579788","https://openalex.org/W2946555236","https://openalex.org/W2947445680","https://openalex.org/W2954386831","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2964058413","https://openalex.org/W2972544500","https://openalex.org/W2972659941","https://openalex.org/W2997069303","https://openalex.org/W2998572311","https://openalex.org/W3082130377","https://openalex.org/W3095361818","https://openalex.org/W3095936335","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3143465836","https://openalex.org/W3143523927","https://openalex.org/W3197042120","https://openalex.org/W3200209270","https://openalex.org/W3206503703","https://openalex.org/W4205582447","https://openalex.org/W4210774711","https://openalex.org/W4226075807","https://openalex.org/W4226225516","https://openalex.org/W4232282348","https://openalex.org/W4283768328","https://openalex.org/W6732045268","https://openalex.org/W6772349387","https://openalex.org/W6802128655","https://openalex.org/W6810681921"],"related_works":["https://openalex.org/W160673860","https://openalex.org/W2963642612","https://openalex.org/W4289548080","https://openalex.org/W1585680390","https://openalex.org/W3173587717","https://openalex.org/W2113005879","https://openalex.org/W3165456129","https://openalex.org/W2070517798","https://openalex.org/W4312793562","https://openalex.org/W4229049252"],"abstract_inverted_index":{"Voiceconversion":[0],"(VC)":[1],"refers":[2],"to":[3,13,63,128,181],"the":[4,7,14,19,45,54,96,122,131,137,147,158,161,165,183,188,191],"transformation":[5],"of":[6,10,48,133,160,167,190],"speaker":[8],"identity":[9],"a":[11,81,177],"speech":[12,39,98],"target":[15],"one":[16],"without":[17],"altering":[18],"linguistic":[20],"content.":[21],"As":[22],"recent":[23],"VC":[24,71,84,92,125],"techniques":[25],"have":[26,41,79,108],"made":[27],"significant":[28],"progress,":[29],"implementing":[30],"them":[31],"in":[32,66,72,139,145],"real-world":[33],"scenarios":[34],"is":[35,143],"also":[36],"considered,":[37],"where":[38],"data":[40,93],"some":[42,67],"inevitable":[43],"interferences,":[44],"most":[46],"common":[47],"which":[49,146],"are":[50,59],"background":[51,57],"sounds.":[52],"On":[53],"other":[55],"hand,":[56],"sounds":[58],"informative":[60],"and":[61,94,164],"need":[62],"be":[64],"retained":[65],"applications,":[68],"such":[69],"as":[70,103],"movies/videos.":[73],"To":[74],"address":[75],"these":[76],"issues,":[77],"we":[78,115],"proposed":[80,176],"noisy-to-noisy":[82],"(N2N)":[83],"framework":[85],"that":[86],"does":[87],"not":[88],"rely":[89],"on":[90],"clean":[91],"models":[95],"noisy":[97,152,172],"directly":[99],"by":[100,120],"using":[101],"noise":[102,135,178],"conditions.":[104,153,173],"Previous":[105],"experimental":[106,155],"results":[107,156],"proven":[109],"its":[110,118,168],"effectiveness.":[111],"In":[112],"this":[113],"article,":[114],"further":[116,129],"improve":[117],"performance":[119,138,169],"introducing":[121,134],"pre-trained":[123],"noise-conditioned":[124],"model.":[126],"Moreover,":[127],"explore":[130],"impacts":[132],"conditions,":[136],"more":[140],"realistic":[141],"situations":[142],"evaluated":[144],"training":[148],"set":[149],"possesses":[150],"speaker-dependent":[151],"The":[154],"demonstrate":[157],"effectiveness":[159,189],"pre-training":[162],"strategy":[163],"degradation":[166],"under":[170],"strict":[171],"We":[174],"then":[175],"augmentation":[179,192],"method":[180],"overcome":[182],"limitation.":[184],"Further":[185],"experiments":[186],"showed":[187],"method.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}