{"id":"https://openalex.org/W4297841559","doi":"https://doi.org/10.21437/interspeech.2022-10990","title":"Non-Parallel Voice Conversion for ASR Augmentation","display_name":"Non-Parallel Voice Conversion for ASR Augmentation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841559","doi":"https://doi.org/10.21437/interspeech.2022-10990"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10990","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10990","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/A5025935520","display_name":"Gary Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gary Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024913801","display_name":"Andrew E. Rosenberg","orcid":"https://orcid.org/0000-0002-4536-8824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055592425","display_name":"Fadi Biadsy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fadi Biadsy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027399854","display_name":"Jesse Emond","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesse Emond","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673889","display_name":"Yinghui Huang","orcid":"https://orcid.org/0000-0003-0607-1507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghui Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036214942","display_name":"Pedro Moreno","orcid":"https://orcid.org/0000-0002-5501-5272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3408","last_page":"3412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9839000105857849,"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":0.6985379457473755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44855907559394836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985379457473755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44855907559394836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10990","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10990","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1979651826","https://openalex.org/W2121681768","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2890402938","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2963799213","https://openalex.org/W2972544500","https://openalex.org/W2972849140","https://openalex.org/W3015280134","https://openalex.org/W3015686596","https://openalex.org/W3034794073","https://openalex.org/W3091928890","https://openalex.org/W3095361818","https://openalex.org/W3097017391","https://openalex.org/W3097777922","https://openalex.org/W3097890746","https://openalex.org/W3100378519","https://openalex.org/W3162879338","https://openalex.org/W3210685431","https://openalex.org/W4210690962","https://openalex.org/W4287118044","https://openalex.org/W4287591426","https://openalex.org/W4288079539"],"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":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"needs":[4],"to":[5,8,42,64,105],"be":[6,35,62],"robust":[7,63],"speaker":[9,14,99],"differences.Voice":[10],"Conversion":[11],"(VC)":[12],"modifies":[13],"characteristics":[15],"of":[16,68,74,83,109,120],"input":[17,69],"speech.This":[18,70],"is":[19,56],"an":[20],"attractive":[21],"feature":[22],"for":[23,117],"ASR":[24,44,53,86,106],"data":[25,39],"augmentation.In":[26],"this":[27],"paper,":[28],"we":[29],"demonstrate":[30],"that":[31,58,94],"voice":[32],"conversion":[33],"can":[34],"used":[36],"as":[37],"a":[38,65,75,84,103],"augmentation":[40],"technique":[41],"improve":[43],"performance,":[45],"even":[46],"on":[47],"LibriSpeech,":[48],"which":[49],"contains":[50],"2,456":[51],"speakers.For":[52],"augmentation,":[54],"it":[55],"necessary":[57],"the":[59,72,81,89],"VC":[60,78,90,111,121],"model":[61],"wide":[66],"range":[67],"motivates":[71],"use":[73,82],"non-autoregressive,":[76],"non-parallel":[77],"model,":[79],"and":[80],"pretrained":[85],"encoder":[87],"within":[88],"model.This":[91],"work":[92],"suggests":[93],"despite":[95],"including":[96],"many":[97],"speakers,":[98],"diversity":[100],"may":[101],"remain":[102],"limitation":[104],"quality.Finally,":[107],"interrogation":[108],"our":[110],"performance":[112],"has":[113],"provided":[114],"useful":[115],"metrics":[116],"objective":[118],"evaluation":[119],"quality.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}