{"id":"https://openalex.org/W4392903903","doi":"https://doi.org/10.1109/icassp48485.2024.10448232","title":"GR0: Self-Supervised Global Representation Learning for Zero-Shot Voice Conversion","display_name":"GR0: Self-Supervised Global Representation Learning for Zero-Shot Voice Conversion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903903","doi":"https://doi.org/10.1109/icassp48485.2024.10448232"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100714799","display_name":"Yunyun Wang","orcid":"https://orcid.org/0000-0002-5884-9408"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyun Wang","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10786","last_page":"10790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7225017547607422},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6929808855056763},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6218394041061401},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5509110689163208},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.54749995470047},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.543502688407898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5213667154312134},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5141194462776184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5128629207611084},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.46817654371261597},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4425179362297058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3510062098503113},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.108374685049057},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09587639570236206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225017547607422},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6929808855056763},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6218394041061401},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5509110689163208},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.54749995470047},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.543502688407898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5213667154312134},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5141194462776184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5128629207611084},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.46817654371261597},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4425179362297058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3510062098503113},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.108374685049057},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09587639570236206},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2086381917","https://openalex.org/W2202109488","https://openalex.org/W2785678896","https://openalex.org/W2896457183","https://openalex.org/W2962788625","https://openalex.org/W2962866891","https://openalex.org/W2973049979","https://openalex.org/W2998572311","https://openalex.org/W3015805741","https://openalex.org/W3035725276","https://openalex.org/W3095410713","https://openalex.org/W3096864844","https://openalex.org/W3113822960","https://openalex.org/W3135715136","https://openalex.org/W3140429000","https://openalex.org/W3160652646","https://openalex.org/W3167533889","https://openalex.org/W3196475561","https://openalex.org/W3196667132","https://openalex.org/W3198275944","https://openalex.org/W3209059054","https://openalex.org/W4200483526","https://openalex.org/W4212774754","https://openalex.org/W4224916425","https://openalex.org/W4297817572","https://openalex.org/W4297841868","https://openalex.org/W4313679638","https://openalex.org/W4381786045","https://openalex.org/W6748582592","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6755257315","https://openalex.org/W6767111847","https://openalex.org/W6774314701","https://openalex.org/W6779841522","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6791753252","https://openalex.org/W6803547063","https://openalex.org/W6805710207","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Research":[0],"in":[1,95],"generative":[2,18],"self-supervised":[3],"learning":[4],"(SSL)":[5],"has":[6],"largely":[7],"focused":[8],"on":[9,83],"local":[10,30],"embeddings":[11],"for":[12,101],"tokenized":[13],"sequences.":[14],"We":[15,32],"introduce":[16],"a":[17,23,39,44,61,70],"SSL":[19],"framework":[20],"that":[21,26,88],"learns":[22],"global":[24,40],"representation":[25],"is":[27],"disentangled":[28],"from":[29],"embeddings.":[31],"apply":[33],"this":[34],"technique":[35],"to":[36,53,75],"jointly":[37],"learn":[38],"speaker":[41,99],"embedding":[42],"and":[43,98,104],"zero-shot":[45],"voice":[46],"converter.":[47],"The":[48],"converter":[49],"modifies":[50],"recorded":[51],"speech":[52],"sound":[54],"as":[55],"if":[56],"it":[57],"were":[58],"spoken":[59],"by":[60],"different":[62],"person":[63],"while":[64],"preserving":[65],"the":[66,76],"content,":[67],"using":[68],"only":[69],"short":[71],"reference":[72],"clip":[73],"unavailable":[74],"model":[77],"during":[78],"training.":[79],"Listening":[80],"experiments":[81],"conducted":[82],"an":[84],"unseen":[85,105],"dataset":[86],"show":[87],"our":[89],"models":[90],"significantly":[91],"outperform":[92],"SOTA":[93],"baselines":[94],"both":[96],"quality":[97],"similarity":[100],"various":[102],"datasets":[103],"languages.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
