{"id":"https://openalex.org/W4226075807","doi":"https://doi.org/10.1109/icassp43922.2022.9747894","title":"Direct Noisy Speech Modeling for Noisy-To-Noisy Voice Conversion","display_name":"Direct Noisy Speech Modeling for Noisy-To-Noisy Voice Conversion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226075807","doi":"https://doi.org/10.1109/icassp43922.2022.9747894"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747894","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5045231545","display_name":"Chao Xie","orcid":"https://orcid.org/0000-0001-7542-1270"},"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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"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":"Yi-Chiao Wu","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"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":"Patrick Lumban Tobing","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"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":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, 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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, 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":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6787","last_page":"6791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9979000091552734,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9782000184059143,"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/computer-science","display_name":"Computer science","score":0.7664741277694702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7361037135124207},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4738911986351013},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4681779444217682},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4303673505783081},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4160376489162445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.362024188041687},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24462023377418518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664741277694702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7361037135124207},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4738911986351013},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4681779444217682},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4303673505783081},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4160376489162445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.362024188041687},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24462023377418518},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747894","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1482298176","https://openalex.org/W2107860279","https://openalex.org/W2159202424","https://openalex.org/W2577350056","https://openalex.org/W2603567530","https://openalex.org/W2752796333","https://openalex.org/W2907262790","https://openalex.org/W2963035245","https://openalex.org/W2963799213","https://openalex.org/W2964058413","https://openalex.org/W2997069303","https://openalex.org/W3012498027","https://openalex.org/W3016007107","https://openalex.org/W3082130377","https://openalex.org/W3095361818","https://openalex.org/W3096408984","https://openalex.org/W3097017391","https://openalex.org/W3163464523","https://openalex.org/W3194805633","https://openalex.org/W3200209270","https://openalex.org/W4231961043","https://openalex.org/W4249468441","https://openalex.org/W4298580827","https://openalex.org/W6628615481","https://openalex.org/W6732045268","https://openalex.org/W6748409065","https://openalex.org/W6802128655"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2275432853","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Beyond":[0],"the":[1,7,14,17,41,63,68,85,88,94,98,111,118,124,138,156],"conventional":[2],"voice":[3,42],"conversion":[4],"(VC)":[5],"where":[6,40],"speaker":[8],"information":[9],"is":[10,43,91],"converted":[11],"without":[12],"altering":[13],"linguistic":[15],"content,":[16],"background":[18,46,69,86,125],"sounds":[19],"are":[20],"informative":[21],"and":[22,36,79,141],"need":[23],"to":[24,61,93,115,155],"be":[25],"retained":[26],"in":[27,34,38,106,146],"some":[28],"real-world":[29],"scenarios,":[30],"such":[31],"as":[32],"VC":[33,37,51,59,81,89,113],"movie/video":[35],"music":[39],"entangled":[44],"with":[45],"sounds.":[47,70,126],"As":[48],"a":[49,56,76,80],"new":[50],"framework,":[52],"we":[53,109],"have":[54,130],"developed":[55],"noisy-to-noisy":[57],"(N2N)":[58],"framework":[60,73,135],"convert":[62],"speaker\u2019s":[64],"identity":[65],"while":[66,122,150],"preserving":[67],"Although":[71],"our":[72,133,160],"consisting":[74],"of":[75,148,159],"denoising":[77,99],"module":[78,82,90,114],"well":[83],"handles":[84],"sounds,":[87],"sensitive":[92],"distortion":[95,104],"caused":[96],"by":[97],"module.":[100],"To":[101],"address":[102],"this":[103,107],"issue,":[105],"paper":[108],"propose":[110],"improved":[112,134],"directly":[116],"model":[117],"noisy":[119],"speech":[120],"waveform":[121],"controlling":[123],"The":[127],"experimental":[128],"results":[129],"demonstrated":[131],"that":[132],"significantly":[136],"outperforms":[137],"previous":[139],"one":[140],"achieves":[142],"an":[143],"acceptable":[144],"score":[145],"terms":[147],"naturalness,":[149],"reaching":[151],"comparable":[152],"similarity":[153],"performance":[154],"upper":[157],"bound":[158],"framework.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}