{"id":"https://openalex.org/W4297841639","doi":"https://doi.org/10.21437/interspeech.2022-322","title":"GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion","display_name":"GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841639","doi":"https://doi.org/10.21437/interspeech.2022-322"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-322","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-322","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":"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/A5036460629","display_name":"Magdalena Proszewska","orcid":"https://orcid.org/0000-0002-5523-2197"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Magdalena Proszewska","raw_affiliation_strings":["Jagiellonian University, Poland"],"affiliations":[{"raw_affiliation_string":"Jagiellonian University, Poland","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045200344","display_name":"Grzegorz Beringer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grzegorz Beringer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087232606","display_name":"Daniel S\u00e1ez-Trigueros","orcid":"https://orcid.org/0000-0001-9623-7472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel S\u00e1ez-Trigueros","raw_affiliation_strings":["Alexa AI"],"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["Alexa AI"],"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027412678","display_name":"Abdelhamid Ezzerg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelhamid Ezzerg","raw_affiliation_strings":["Alexa AI"],"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Alexa AI"],"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036460629"],"corresponding_institution_ids":["https://openalex.org/I126596746"],"apc_list":null,"apc_paid":null,"fwci":0.6233,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67630899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2973","last_page":"2977"},"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":0.9961000084877014,"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":0.9739000201225281,"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/spectrogram","display_name":"Spectrogram","score":0.8327201008796692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6939359903335571},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6471362113952637},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5158807039260864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4280685484409332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3647225499153137}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8327201008796692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6939359903335571},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6471362113952637},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5158807039260864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4280685484409332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3647225499153137},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-322","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-322","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2805669069","https://openalex.org/W2806000759","https://openalex.org/W2903739847","https://openalex.org/W2938583109","https://openalex.org/W2945478979","https://openalex.org/W2963799213","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W3022876224","https://openalex.org/W3026874504","https://openalex.org/W3095990227","https://openalex.org/W3096567388","https://openalex.org/W3096864844","https://openalex.org/W3162770051","https://openalex.org/W3195171908","https://openalex.org/W3196584150","https://openalex.org/W3196702840","https://openalex.org/W3197113339","https://openalex.org/W3197991492","https://openalex.org/W4288079858","https://openalex.org/W4288079962","https://openalex.org/W4288337064","https://openalex.org/W4289761690"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,130],"propose":[4],"GlowVC:":[5],"a":[6],"multilingual":[7],"multispeaker":[8],"flow-based":[9],"model":[10],"for":[11,37,95],"language-independent":[12],"text-free":[13],"voice":[14],"conversion.We":[15],"build":[16],"on":[17],"Glow-TTS,":[18],"which":[19],"provides":[20],"an":[21],"architecture":[22],"that":[23,132],"enables":[24],"use":[25],"of":[26,34,43,52,89,111,141],"linguistic":[27],"features":[28],"during":[29],"training":[30],"without":[31],"the":[32,50,59,69,127],"necessity":[33],"using":[35],"them":[36],"VC":[38],"inference.We":[39],"consider":[40],"two":[41],"versions":[42],"our":[44,85],"model:":[45],"GlowVC-conditional":[46,136],"and":[47,57,75,93,101,123,137],"GlowVC-explicit.GlowVC-conditional":[48],"models":[49,68,86,104],"distribution":[51,71],"mel-spectrograms":[53],"with":[54,72],"speaker-conditioned":[55],"flow":[56,74],"disentangles":[58,76],"mel-spectrogram":[60],"space":[61,78],"into":[62,79],"content-and":[63],"pitchrelevant":[64],"dimensions,":[65],"while":[66,113],"GlowVC-explicit":[67,133],"explicit":[70],"unconditioned":[73],"said":[77],"content-,":[80],"pitch-and":[81],"speaker-relevant":[82],"dimensions.We":[83],"evaluate":[84],"in":[87,99,109,120,126,139],"terms":[88,110,140],"intelligibility,":[90,112],"speaker":[91,118],"similarity":[92,119],"naturalness":[94],"intra-and":[96],"cross-lingual":[97,128],"conversion":[98],"seen":[100],"unseen":[102],"languages.GlowVC":[103],"greatly":[105],"outperform":[106],"Au-toVC":[107,138],"baseline":[108],"achieving":[114],"just":[115],"as":[116],"high":[117],"intra-lingual":[121],"VC,":[122],"slightly":[124],"worse":[125],"setting.Moreover,":[129],"demonstrate":[131],"surpasses":[134],"both":[135],"naturalness.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}