{"id":"https://openalex.org/W3155308523","doi":"https://doi.org/10.23919/eusipco54536.2021.9616190","title":"Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels","display_name":"Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3155308523","doi":"https://doi.org/10.23919/eusipco54536.2021.9616190","mag":"3155308523"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616190","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616190","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.07283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041851676","display_name":"Cl\u00e9ment Le Moine","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Clement Le Moine","raw_affiliation_strings":["STMS Lab, IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"STMS Lab, IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306"},"institutions":[{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Obin","raw_affiliation_strings":["STMS Lab, IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"STMS Lab, IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065828059","display_name":"Axel R\u00f6ebel","orcid":"https://orcid.org/0000-0001-6136-4391"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Roebel","raw_affiliation_strings":["STMS Lab, IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"STMS Lab, IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041851676"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"],"apc_list":null,"apc_paid":null,"fwci":1.1424,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81110803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"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":0.9995999932289124,"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":0.9966999888420105,"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/convolution","display_name":"Convolution (computer science)","score":0.7096420526504517},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6978504657745361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6963070631027222},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6203868985176086},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6148231625556946},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6059001684188843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5137368440628052},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.49442267417907715},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4300921857357025},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.42161253094673157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3372713327407837},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2994263768196106}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7096420526504517},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6978504657745361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963070631027222},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6203868985176086},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6148231625556946},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6059001684188843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5137368440628052},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.49442267417907715},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4300921857357025},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.42161253094673157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3372713327407837},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2994263768196106},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616190","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616190","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.07283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07283","pdf_url":"https://arxiv.org/pdf/2104.07283","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-03239583v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03239583","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EUSIPCO, 2021, Dublin (virtual ), Ireland","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2104.07283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.07283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.07283","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07283","pdf_url":"https://arxiv.org/pdf/2104.07283","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1975079546","https://openalex.org/W2034139177","https://openalex.org/W2099471712","https://openalex.org/W2106421426","https://openalex.org/W2158504378","https://openalex.org/W2184310502","https://openalex.org/W2185573909","https://openalex.org/W2407110532","https://openalex.org/W2517513811","https://openalex.org/W2733239165","https://openalex.org/W2740504963","https://openalex.org/W2747914378","https://openalex.org/W2794490148","https://openalex.org/W2808514527","https://openalex.org/W2889544410","https://openalex.org/W2902070858","https://openalex.org/W2919171658","https://openalex.org/W2950542544","https://openalex.org/W3004402693","https://openalex.org/W3015935472","https://openalex.org/W3025044797","https://openalex.org/W3025680351","https://openalex.org/W3026640763","https://openalex.org/W3096939667","https://openalex.org/W4320013936","https://openalex.org/W6686269052"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2382174632","https://openalex.org/W2129959498","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W2784060934","https://openalex.org/W2902714807","https://openalex.org/W2077021924"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,25,39,60,87],"end-to-end":[4,88],"framework":[5],"for":[6],"the":[7,11,47,68,90,99,103],"F0":[8,32,73,91,105],"transformation":[9,48],"in":[10,23,86],"context":[12],"of":[13,59,72],"expressive":[14],"voice":[15],"conversion.":[16],"A":[17],"single":[18,80],"neural":[19],"network":[20,82],"is":[21,28,43,57],"proposed,":[22],"which":[24],"first":[26,55],"module":[27,42,56],"used":[29,44],"to":[30,45,52,84,98],"learn":[31,46,85],"representation":[33],"over":[34],"different":[35],"temporal":[36,70],"scales":[37,71],"and":[38],"second":[40],"adversarial":[41],"from":[49,102],"one":[50],"emotion":[51],"another.":[53],"The":[54,79],"composed":[58],"convolution":[61],"layer":[62],"with":[63,96],"wavelet":[64],"kernels":[65],"so":[66],"that":[67,93],"various":[69],"variations":[74],"can":[75],"be":[76],"efficiently":[77],"encoded.":[78],"decomposition/transformation":[81],"allows":[83],"manner":[89],"decomposition":[92],"are":[94],"optimal":[95],"respect":[97],"transformation,":[100],"directly":[101],"raw":[104],"signal.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-04-26T00:00:00"}