{"id":"https://openalex.org/W7116093375","doi":"https://doi.org/10.1007/s00371-025-04201-3","title":"Application of the fast diffusion model ST-diffusion in multi-modal lip-to-speech generation","display_name":"Application of the fast diffusion model ST-diffusion in multi-modal lip-to-speech generation","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7116093375","doi":"https://doi.org/10.1007/s00371-025-04201-3"},"language":"en","primary_location":{"id":"doi:10.1007/s00371-025-04201-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00371-025-04201-3","pdf_url":null,"source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Visual Computer","raw_type":"journal-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":null,"display_name":"Qiong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiong Yang","raw_affiliation_strings":["School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","Shaanxi Key Laboratory of Clothing Intelligence, School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]},{"raw_affiliation_string":"Shaanxi Key Laboratory of Clothing Intelligence, School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuxuan Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxuan Bai","raw_affiliation_strings":["School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","Shaanxi Key Laboratory of Clothing Intelligence, School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]},{"raw_affiliation_string":"Shaanxi Key Laboratory of Clothing Intelligence, School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ying Li","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","Shaanxi Key Laboratory of Clothing Intelligence, School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]},{"raw_affiliation_string":"Shaanxi Key Laboratory of Clothing Intelligence, School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an, 710048, Shaanxi, China","institution_ids":["https://openalex.org/I27599042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27599042"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.9024,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80439834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"42","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.843999981880188,"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":0.843999981880188,"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/T11448","display_name":"Face recognition and analysis","score":0.10849999636411667,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.007400000002235174,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7597000002861023},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.45719999074935913},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45649999380111694},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.45570001006126404},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.44769999384880066},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.42669999599456787},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.39410001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803600013256073},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7597000002861023},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.39410001039505005},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00371-025-04201-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00371-025-04201-3","pdf_url":null,"source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Visual Computer","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2147871138","https://openalex.org/W2585824449","https://openalex.org/W2598634450","https://openalex.org/W2963030892","https://openalex.org/W2964352155","https://openalex.org/W2997540481","https://openalex.org/W3010290582","https://openalex.org/W3035626590","https://openalex.org/W3128211327","https://openalex.org/W3129651364","https://openalex.org/W3163658555","https://openalex.org/W3184761438","https://openalex.org/W4307536105","https://openalex.org/W4360884927","https://openalex.org/W4361193053","https://openalex.org/W4379919367","https://openalex.org/W4384811738","https://openalex.org/W4385275839","https://openalex.org/W4386044226","https://openalex.org/W4392136979","https://openalex.org/W4392697818","https://openalex.org/W4392903433","https://openalex.org/W4399940039","https://openalex.org/W4401250631","https://openalex.org/W4401694110","https://openalex.org/W4406131770","https://openalex.org/W4407051281","https://openalex.org/W6891986677","https://openalex.org/W6947872501"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-12-19T00:00:00"}
