{"id":"https://openalex.org/W4402112175","doi":"https://doi.org/10.21437/interspeech.2024-1989","title":"Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models","display_name":"Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112175","doi":"https://doi.org/10.21437/interspeech.2024-1989"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1989","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1989","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":"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/A5101921729","display_name":"Weiqin Li","orcid":"https://orcid.org/0000-0003-3822-511X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiqin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020072783","display_name":"Peiji Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiji Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041879065","display_name":"Yicheng Zhong","orcid":"https://orcid.org/0000-0001-7661-5384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicheng Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089348821","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-4984-2252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757057","display_name":"Zhisheng Wang","orcid":"https://orcid.org/0000-0002-2907-755X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhisheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8448,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92453179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1785","last_page":"1789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9799000024795532,"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/T12031","display_name":"Speech and dialogue systems","score":0.9799000024795532,"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":0.9555000066757202,"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":0.920199990272522,"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":0.689245343208313},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6230928897857666},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48093312978744507},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45426836609840393},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45169636607170105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36955612897872925},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08704987168312073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689245343208313},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6230928897857666},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48093312978744507},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45426836609840393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45169636607170105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36955612897872925},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08704987168312073},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1989","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1989","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W632157940","https://openalex.org/W2387981414","https://openalex.org/W127416991"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
