{"id":"https://openalex.org/W4385823402","doi":"https://doi.org/10.21437/interspeech.2023-715","title":"Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model","display_name":"Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823402","doi":"https://doi.org/10.21437/interspeech.2023-715"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-715","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-715","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":"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/A5100631401","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0003-0569-2176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102313170","display_name":"Max W. Y. Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Max W. Y. Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100527262","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-1869-0594"},"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/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Weng","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":0.6534,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68263108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4858","last_page":"4862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9714999794960022,"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":0.9714999794960022,"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/prosody","display_name":"Prosody","score":0.8274949789047241},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6828141808509827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6693875789642334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6563959121704102},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5056407451629639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.428394079208374},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.41853955388069153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35566800832748413},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05713289976119995}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8274949789047241},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6828141808509827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6693875789642334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563959121704102},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5056407451629639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.428394079208374},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41853955388069153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35566800832748413},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05713289976119995},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-715","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-715","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":[{"display_name":"Reduced inequalities","score":0.5,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W2750037515","https://openalex.org/W4319862652","https://openalex.org/W2394249171","https://openalex.org/W2031981373"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
