{"id":"https://openalex.org/W3127854286","doi":"https://doi.org/10.1109/icassp39728.2021.9414235","title":"Self-Supervised VQ-VAE for One-Shot Music Style Transfer","display_name":"Self-Supervised VQ-VAE for One-Shot Music Style Transfer","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3127854286","doi":"https://doi.org/10.1109/icassp39728.2021.9414235","mag":"3127854286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.05749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073040966","display_name":"Ond\u0159ej C\u00edfka","orcid":"https://orcid.org/0000-0002-6268-6445"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I2885711838","display_name":"TDF (France)","ror":"https://ror.org/01866as23","country_code":"FR","type":"company","lineage":["https://openalex.org/I2885711838"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ondrej Cifka","raw_affiliation_strings":["Inter Digital R & D, Cesson-S\u00e9vign\u00e9, France","LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","InterDigital R&D France (Le Rainbow, 975 Avenue des Champs Blancs, 35510 Cesson-S\u00e9vign\u00e9 - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","IP Paris - Institut Polytechnique de Paris (France)","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inter Digital R & D, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I2885711838"]},{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"InterDigital R&D France (Le Rainbow, 975 Avenue des Champs Blancs, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":[]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073788938","display_name":"Alexey Ozerov","orcid":"https://orcid.org/0000-0003-4834-5166"},"institutions":[{"id":"https://openalex.org/I2885711838","display_name":"TDF (France)","ror":"https://ror.org/01866as23","country_code":"FR","type":"company","lineage":["https://openalex.org/I2885711838"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexey Ozerov","raw_affiliation_strings":["Inter Digital R & D, Cesson-S\u00e9vign\u00e9, France","InterDigital R&D France (Le Rainbow, 975 Avenue des Champs Blancs, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inter Digital R & D, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I2885711838"]},{"raw_affiliation_string":"InterDigital R&D France (Le Rainbow, 975 Avenue des Champs Blancs, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053326908","display_name":"Umut \u015eim\u015fekli","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Umut Simsekli","raw_affiliation_strings":["Inria/ENS, Paris, France","LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","IP Paris - Institut Polytechnique de Paris (France)","SIERRA - Statistical Machine Learning and Parsimony (France)","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria/ENS, Paris, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I29607241"]},{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"SIERRA - Statistical Machine Learning and Parsimony (France)","institution_ids":[]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","IP Paris - Institut Polytechnique de Paris (France)","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3928,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.8919577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.992900013923645,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9847000241279602,"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/autoencoder","display_name":"Autoencoder","score":0.8290177583694458},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7697210311889648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695685029029846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5918015241622925},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5513687133789062},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5126873254776001},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5069708824157715},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.49565446376800537},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.48378822207450867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4008510708808899},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2551531195640564},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23298263549804688}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8290177583694458},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7697210311889648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695685029029846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5918015241622925},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5513687133789062},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5126873254776001},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5069708824157715},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.49565446376800537},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.48378822207450867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4008510708808899},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2551531195640564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23298263549804688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.05749","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.05749","pdf_url":"https://arxiv.org/pdf/2102.05749","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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03132940v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-03132940","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2021, Toronto / Virtual, Canada. &#x27E8;10.1109/ICASSP39728.2021.9414235&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.05749","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.05749","pdf_url":"https://arxiv.org/pdf/2102.05749","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2385545","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1976069042","https://openalex.org/W2015433306","https://openalex.org/W2120847449","https://openalex.org/W2157331557","https://openalex.org/W2405581548","https://openalex.org/W2475287302","https://openalex.org/W2475687244","https://openalex.org/W2519091744","https://openalex.org/W2603777577","https://openalex.org/W2752796333","https://openalex.org/W2766465839","https://openalex.org/W2785325870","https://openalex.org/W2799087757","https://openalex.org/W2803963372","https://openalex.org/W2811079561","https://openalex.org/W2903005299","https://openalex.org/W2909535979","https://openalex.org/W2941810372","https://openalex.org/W2954914497","https://openalex.org/W2962942158","https://openalex.org/W2963233633","https://openalex.org/W2963420272","https://openalex.org/W2963485424","https://openalex.org/W2963775347","https://openalex.org/W2963799213","https://openalex.org/W2963889406","https://openalex.org/W2964121744","https://openalex.org/W2989955315","https://openalex.org/W2995233853","https://openalex.org/W3000389243","https://openalex.org/W3040787347","https://openalex.org/W3049637270","https://openalex.org/W3080857286","https://openalex.org/W3097059217","https://openalex.org/W3109050852","https://openalex.org/W3112895167","https://openalex.org/W3162366763","https://openalex.org/W4287666817","https://openalex.org/W4293568215","https://openalex.org/W6600110733","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6747899497","https://openalex.org/W6752901844","https://openalex.org/W6753018729","https://openalex.org/W6756038284","https://openalex.org/W6757028937","https://openalex.org/W6762464424","https://openalex.org/W6765147365","https://openalex.org/W6771763809","https://openalex.org/W6780323268","https://openalex.org/W6782602824","https://openalex.org/W6784348365","https://openalex.org/W6785363610","https://openalex.org/W6787084273"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2406877384","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Neural":[0],"style":[1,8,45,63,76],"transfer,":[2],"allowing":[3],"to":[4,12,49,126,150],"apply":[5],"the":[6,18,34,57,67,70,94,113,136],"artistic":[7],"of":[9,17,60,72,96,112,130,141],"one":[10,16],"image":[11,62],"another,":[13],"has":[14],"become":[15],"most":[19,55],"widely":[20],"showcased":[21],"computer":[22],"vision":[23],"applications":[24],"shortly":[25],"after":[26],"its":[27],"introduction.":[28],"In":[29,86],"contrast,":[30],"related":[31],"tasks":[32],"in":[33,93],"music":[35],"audio":[36,75],"domain":[37],"remained,":[38],"until":[39],"recently,":[40],"largely":[41],"untackled.":[42],"While":[43],"several":[44],"conversion":[46],"methods":[47,78],"tailored":[48],"musical":[50,80],"signals":[51],"have":[52],"been":[53],"proposed,":[54],"lack":[56],"\u2018one-shot\u2019":[58],"capability":[59],"classical":[61],"transfer":[64,77],"algorithms.":[65],"On":[66],"other":[68],"hand,":[69],"results":[71],"existing":[73],"one-shot":[74,97],"on":[79,109],"inputs":[81],"are":[82,90],"not":[83],"as":[84],"compelling.":[85],"this":[87,106],"work,":[88],"we":[89],"specifically":[91],"interested":[92],"problem":[95],"timbre":[98,131],"transfer.":[99],"We":[100,134],"present":[101],"a":[102,120,139],"novel":[103],"method":[104,137],"for":[105],"task,":[107],"based":[108],"an":[110],"extension":[111],"vector-quantized":[114],"variational":[115],"autoencoder":[116],"(VQ-VAE),":[117],"along":[118],"with":[119],"simple":[121],"self-supervised":[122],"learning":[123],"strategy":[124],"designed":[125],"obtain":[127],"disentangled":[128],"representations":[129],"and":[132,144],"pitch.":[133],"evaluate":[135],"using":[138],"set":[140],"objective":[142],"metrics":[143],"show":[145],"that":[146],"it":[147],"is":[148],"able":[149],"outperform":[151],"selected":[152],"baselines.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}
