{"id":"https://openalex.org/W4283768328","doi":"https://doi.org/10.21437/interspeech.2022-10158","title":"An Evaluation of Three-Stage Voice Conversion Framework for Noisy and Reverberant Conditions","display_name":"An Evaluation of Three-Stage Voice Conversion Framework for Noisy and Reverberant Conditions","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283768328","doi":"https://doi.org/10.21437/interspeech.2022-10158"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10158","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10158","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5047211536","display_name":"Yeonjong Choi","orcid":null},"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":"Yeonjong Choi","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100532258","display_name":"Chao Xie","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4910","last_page":"4914"},"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7078148722648621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.608368456363678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078148722648621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.608368456363678}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10158","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10158","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2107860279","https://openalex.org/W2127851351","https://openalex.org/W2159202424","https://openalex.org/W2164502538","https://openalex.org/W2242818861","https://openalex.org/W2576309025","https://openalex.org/W2577350056","https://openalex.org/W2889540509","https://openalex.org/W2962935966","https://openalex.org/W2963035245","https://openalex.org/W2963197115","https://openalex.org/W2964058413","https://openalex.org/W2997069303","https://openalex.org/W3015191643","https://openalex.org/W3082130377","https://openalex.org/W3095361818","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3098557217","https://openalex.org/W3194805633","https://openalex.org/W3200209270","https://openalex.org/W4226075807","https://openalex.org/W4287632494","https://openalex.org/W4306291601"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,86,95,102,109,115],"new":[4],"voice":[5],"conversion":[6],"(VC)":[7],"framework":[8,89],"capable":[9],"of":[10,72,79],"dealing":[11],"with":[12,37,43,67],"both":[13,142],"additive":[14],"noise":[15,39,123,143],"and":[16,18,40,105,124,144,146,158,167],"reverberation,":[17,145],"its":[19,61],"performance":[20,62,130],"evaluation.There":[21],"have":[22],"been":[23],"studied":[24],"some":[25],"VC":[26,68,88,106,111,129,175],"researches":[27],"focusing":[28],"on":[29,91,114,153,174],"real-world":[30],"circumstances":[31],"where":[32,47],"speech":[33,74,82,156],"data":[34],"are":[35],"interfered":[36],"background":[38],"reverberation.To":[41],"deal":[42],"more":[44],"practical":[45],"conditions":[46],"no":[48],"clean":[49],"target":[50,73,81],"dataset":[51],"is":[52,57],"available,":[53],"one":[54],"possible":[55],"approach":[56],"zero-shot":[58],"VC,":[59],"but":[60],"tends":[63],"to":[64],"degrade":[65],"compared":[66],"using":[69,94,101,108],"sufficient":[70],"amount":[71,78],"data.To":[75],"leverage":[76],"large":[77],"noisy-reverberant":[80,155],"data,":[83,157],"we":[84],"propose":[85],"three-stage":[87],"based":[90,113],"denoising":[92,97,166],"process":[93,100,107],"pretrained":[96],"model,":[98,104],"dereverberation":[99,103,168],"nonparallel":[110],"model":[112],"variational":[116],"autoencoder.The":[117],"experimental":[118],"results":[119],"show":[120],"that":[121],"1)":[122],"reverberation":[125],"additively":[126],"cause":[127],"significant":[128],"degradation,":[131],"2)":[132],"the":[133,137,149,154,160,165],"proposed":[134],"method":[135],"alleviates":[136],"adverse":[138,172],"effects":[139,173],"caused":[140],"by":[141,164],"significantly":[147],"outperforms":[148],"baseline":[150],"directly":[151],"trained":[152],"3)":[159],"potential":[161],"degradation":[162],"introduced":[163],"still":[169],"causes":[170],"noticeable":[171],"performance.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}