{"id":"https://openalex.org/W4385823407","doi":"https://doi.org/10.21437/interspeech.2023-289","title":"Prosody Modeling with 3D Visual Information for Expressive Video Dubbing","display_name":"Prosody Modeling with 3D Visual Information for Expressive Video Dubbing","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823407","doi":"https://doi.org/10.21437/interspeech.2023-289"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-289","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-289","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/A5024368167","display_name":"Zhihan Yang","orcid":"https://orcid.org/0009-0004-1659-1404"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhihan Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shansong Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233956","display_name":"Xu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017383334","display_name":"Haozhe Wu","orcid":"https://orcid.org/0000-0002-3036-6930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haozhe Wu","raw_affiliation_strings":[],"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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018208648","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0003-2539-3368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024368167"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5237,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71169873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4863","last_page":"4867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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":0.9900000095367432,"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/T11309","display_name":"Music and Audio Processing","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7386913299560547},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6385830640792847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35497990250587463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386913299560547},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6385830640792847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35497990250587463}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-289","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-289","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/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}