{"id":"https://openalex.org/W4415432606","doi":"https://doi.org/10.21437/interspeech.2025-2684","title":"Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion","display_name":"Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432606","doi":"https://doi.org/10.21437/interspeech.2025-2684"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2684","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5113251188","display_name":"Kaidi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kaidi Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310824","display_name":"Wenhao Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Guan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083611896","display_name":"Ziyue Karen Jiang","orcid":"https://orcid.org/0009-0007-4158-4689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyue Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692702","display_name":"Hukai Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hukai Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016035496","display_name":"Peijie Chen","orcid":"https://orcid.org/0000-0003-2075-3133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peijie Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100528811","display_name":"Weijie Wu","orcid":"https://orcid.org/0009-0001-4621-7243"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijie Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100388495","display_name":"Chunlin Li","orcid":"https://orcid.org/0000-0003-3723-5703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5113251188"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16627779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1383","last_page":"1387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9739000201225281,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9596999883651733,"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/feature","display_name":"Feature (linguistics)","score":0.3488999903202057},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2732999920845032},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24289999902248383},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.23810000717639923},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.23659999668598175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43459999561309814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24289999902248383},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.23810000717639923},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.23659999668598175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23199999332427979}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2684","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
