{"id":"https://openalex.org/W4402112067","doi":"https://doi.org/10.21437/interspeech.2024-2362","title":"Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy","display_name":"Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112067","doi":"https://doi.org/10.21437/interspeech.2024-2362"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2362","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5101380919","display_name":"Linhan Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Linhan Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108604484","display_name":"Yuanjun Lv","orcid":"https://orcid.org/0009-0002-2272-9153"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanjun Lv","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106698700","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-8075-1784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332221","display_name":"Ziqian Wang","orcid":"https://orcid.org/0000-0001-8113-9941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqian Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069977860","display_name":"Wendi He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wendi He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102934648","display_name":"Hongbin Zhou","orcid":"https://orcid.org/0000-0002-7133-8987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102528709","display_name":"Lei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101380919"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75247366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2745","last_page":"2749"},"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":0.9905999898910522,"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/T12031","display_name":"Speech and dialogue systems","score":0.9758999943733215,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6989067196846008},{"id":"https://openalex.org/keywords/dual-mode","display_name":"Dual mode","score":0.6621118783950806},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6073595881462097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5722379684448242},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5720260143280029},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.5551806688308716},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4288843274116516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4205387234687805},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3360748291015625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2856947183609009},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26046329736709595},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.2092633843421936},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.20502451062202454},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.18618953227996826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16420644521713257}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6989067196846008},{"id":"https://openalex.org/C3019325349","wikidata":"https://www.wikidata.org/wiki/Q3874753","display_name":"Dual mode","level":2,"score":0.6621118783950806},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6073595881462097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5722379684448242},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5720260143280029},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.5551806688308716},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4288843274116516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4205387234687805},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3360748291015625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2856947183609009},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26046329736709595},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2092633843421936},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.20502451062202454},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.18618953227996826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16420644521713257},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-2362","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2392631856","https://openalex.org/W4379400065","https://openalex.org/W2958550830","https://openalex.org/W2355651228","https://openalex.org/W2330491326","https://openalex.org/W2768219827","https://openalex.org/W1992581387","https://openalex.org/W4254025658"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
