{"id":"https://openalex.org/W4385823160","doi":"https://doi.org/10.21437/interspeech.2023-754","title":"ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models","display_name":"ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823160","doi":"https://doi.org/10.21437/interspeech.2023-754"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-754","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5081329998","display_name":"Minki Kang","orcid":"https://orcid.org/0000-0002-5440-6589"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minki Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054823037","display_name":"Wooseok Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wooseok Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070302452","display_name":"Sung Ju Hwang","orcid":"https://orcid.org/0000-0002-9675-2324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung Ju Hwang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086698569","display_name":"Eunho Yang","orcid":"https://orcid.org/0000-0003-2188-0169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunho Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081329998"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7379,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87638366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4339","last_page":"4343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9761999845504761,"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":0.9761999845504761,"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/T12031","display_name":"Speech and dialogue systems","score":0.9458000063896179,"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":0.9370999932289124,"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/zero","display_name":"Zero (linguistics)","score":0.6496226787567139},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6364812850952148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6303138732910156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6047046184539795},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.587013304233551},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.47223329544067383},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4288432002067566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.326591432094574},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12114492058753967},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08954238891601562},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07670480012893677},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.050445109605789185}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6496226787567139},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6364812850952148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6303138732910156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6047046184539795},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.587013304233551},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.47223329544067383},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4288432002067566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.326591432094574},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12114492058753967},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08954238891601562},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07670480012893677},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.050445109605789185},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-754","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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":["https://openalex.org/W4307315102","https://openalex.org/W2981091784","https://openalex.org/W2368779261","https://openalex.org/W2353463996","https://openalex.org/W4306975314","https://openalex.org/W2778699561","https://openalex.org/W4379539688","https://openalex.org/W2579204149","https://openalex.org/W4255510578","https://openalex.org/W2102737569"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
