{"id":"https://openalex.org/W4402111357","doi":"https://doi.org/10.21437/interspeech.2024-1432","title":"DreamVoice: Text-Guided Voice Conversion","display_name":"DreamVoice: Text-Guided Voice Conversion","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111357","doi":"https://doi.org/10.21437/interspeech.2024-1432"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1432","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/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078637653","display_name":"Karan Thakkar","orcid":"https://orcid.org/0000-0002-6803-1116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karan Thakkar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052261160","display_name":"Zengyi Qin","orcid":"https://orcid.org/0000-0002-5477-9764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengyi Qin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048171604"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3264,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83777729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4373","last_page":"4377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9643999934196472,"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":0.9643999934196472,"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/computer-science","display_name":"Computer science","score":0.6854397058486938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5121722221374512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3572411835193634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854397058486938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5121722221374512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3572411835193634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1432","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/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
