{"id":"https://openalex.org/W4385823403","doi":"https://doi.org/10.21437/interspeech.2023-194","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","display_name":"Intelligible Lip-to-Speech Synthesis with Speech Units","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823403","doi":"https://doi.org/10.21437/interspeech.2023-194"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-194","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/A5101725649","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0009-0005-6817-604X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeongsoo Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Man Ro","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":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4349","last_page":"4353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9375,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9375,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7428622245788574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6630871295928955},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6378012895584106},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4151894450187683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3598286509513855}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7428622245788574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6630871295928955},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6378012895584106},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4151894450187683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3598286509513855}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-194","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1658560081","https://openalex.org/W2588431733","https://openalex.org/W2102737569","https://openalex.org/W2254895521","https://openalex.org/W3002577753","https://openalex.org/W2142819117","https://openalex.org/W1890221585","https://openalex.org/W2036980031","https://openalex.org/W2120260542","https://openalex.org/W2117676474"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}