{"id":"https://openalex.org/W4417351280","doi":"https://doi.org/10.1016/j.csl.2025.101924","title":"Audiovisual speech enhancement and voice activity detection using generative and regressive visual features","display_name":"Audiovisual speech enhancement and voice activity detection using generative and regressive visual features","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W4417351280","doi":"https://doi.org/10.1016/j.csl.2025.101924"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2025.101924","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101924","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","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":"https://openalex.org/A5108743403","display_name":"Cheng Yu","orcid":"https://orcid.org/0000-0001-5544-7449"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, 43210, USA"],"raw_orcid":"https://orcid.org/0000-0001-5544-7449","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009379093","display_name":"Vahid Ahmadi Kalkhorani","orcid":"https://orcid.org/0000-0002-4166-1935"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Ahmadi Kalkhorani","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, 43210, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Reality Labs, Meta, Redmond, WA, 20004, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs, Meta, Redmond, WA, 20004, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108743403"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":null,"fwci":1.0383,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82628895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"99","issue":null,"first_page":"101924","last_page":"101924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9959999918937683,"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":0.0008999999845400453,"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":0.0007999999797903001,"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/robustness","display_name":"Robustness (evolution)","score":0.571399986743927},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5702999830245972},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5401999950408936},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45179998874664307},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4250999987125397},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41850000619888306},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4007999897003174},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8801000118255615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7439000010490417},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.571399986743927},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5702999830245972},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5401999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.csl.2025.101924","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101924","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8683737838","display_name":null,"funder_award_id":"ACI-1928147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W15147940","https://openalex.org/W1677182931","https://openalex.org/W1963970749","https://openalex.org/W2014621385","https://openalex.org/W2067295501","https://openalex.org/W2144404214","https://openalex.org/W2194775991","https://openalex.org/W2289394825","https://openalex.org/W2516001803","https://openalex.org/W2550143307","https://openalex.org/W2612770767","https://openalex.org/W2788241093","https://openalex.org/W2890952074","https://openalex.org/W2900292050","https://openalex.org/W2954930777","https://openalex.org/W2962866211","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2965390715","https://openalex.org/W3015526955","https://openalex.org/W3035626590","https://openalex.org/W3081492798","https://openalex.org/W3097777922","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3119269912","https://openalex.org/W3126260881","https://openalex.org/W3136499730","https://openalex.org/W3137758952","https://openalex.org/W3160071434","https://openalex.org/W3182657421","https://openalex.org/W3196830617","https://openalex.org/W3197832224","https://openalex.org/W4226062543","https://openalex.org/W4295308317","https://openalex.org/W4307286264","https://openalex.org/W4312337341","https://openalex.org/W4312899222","https://openalex.org/W4319862437","https://openalex.org/W4366201642","https://openalex.org/W4372260127","https://openalex.org/W4372342911","https://openalex.org/W4375869169","https://openalex.org/W4380434618","https://openalex.org/W4385756463","https://openalex.org/W4385822341","https://openalex.org/W4386076005","https://openalex.org/W4391021590","https://openalex.org/W4392903305","https://openalex.org/W4392903720","https://openalex.org/W4402112025","https://openalex.org/W4402112360","https://openalex.org/W4402112611","https://openalex.org/W4404102497","https://openalex.org/W4410153306"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-12-15T00:00:00"}