{"id":"https://openalex.org/W3126260881","doi":"https://doi.org/10.1109/icassp43922.2022.9747187","title":"VSEGAN: Visual Speech Enhancement Generative Adversarial Network","display_name":"VSEGAN: Visual Speech Enhancement Generative Adversarial Network","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3126260881","doi":"https://doi.org/10.1109/icassp43922.2022.9747187","mag":"3126260881"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747187","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5050125868","display_name":"Xinmeng Xu","orcid":"https://orcid.org/0009-0008-1607-7180"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Xinmeng Xu","raw_affiliation_strings":["Vivo AI Lab,P. R. China","E. E. Engineering, Trinity College, Dublin, Ireland","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"E. E. Engineering, Trinity College, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714578","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-6815-0879"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Vivo AI Lab,P. R. China","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111066465","display_name":"Dongxiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxiang Xu","raw_affiliation_strings":["Vivo AI Lab,P. R. China","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023155749","display_name":"Yiyuan Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiyuan Peng","raw_affiliation_strings":["Vivo AI Lab,P. R. China","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776528","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0003-2745-1656"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["Vivo AI Lab,P. R. China","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018065603","display_name":"Jie Jia","orcid":"https://orcid.org/0000-0001-7296-5061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Jia","raw_affiliation_strings":["Vivo AI Lab,P. R. China","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687673","display_name":"Binbin Chen","orcid":"https://orcid.org/0000-0002-9584-0082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Chen","raw_affiliation_strings":["Vivo AI Lab,P. R. China","Vivo AI Lab, P. R. China"],"affiliations":[{"raw_affiliation_string":"Vivo AI Lab,P. R. China","institution_ids":[]},{"raw_affiliation_string":"Vivo AI Lab, P. R. China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5050125868"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":1.841,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87677725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7308","last_page":"7311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9905999898910522,"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":0.775067925453186},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7448738813400269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6845449805259705},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6556086540222168},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.520844042301178},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.519004225730896},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.49292635917663574},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4648389518260956},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45289722084999084},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4505777657032013},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43877533078193665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42636778950691223},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3353763818740845},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31116148829460144},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13024947047233582},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.12827709317207336},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07543197274208069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775067925453186},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7448738813400269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6845449805259705},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6556086540222168},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.520844042301178},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.519004225730896},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49292635917663574},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4648389518260956},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45289722084999084},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4505777657032013},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43877533078193665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42636778950691223},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3353763818740845},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31116148829460144},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13024947047233582},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.12827709317207336},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07543197274208069},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747187","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W79317937","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1557133539","https://openalex.org/W1995536493","https://openalex.org/W1999846783","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2044893557","https://openalex.org/W2087681821","https://openalex.org/W2091930743","https://openalex.org/W2094461119","https://openalex.org/W2096779346","https://openalex.org/W2099128937","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2141998673","https://openalex.org/W2154151281","https://openalex.org/W2538403209","https://openalex.org/W2577762507","https://openalex.org/W2593414223","https://openalex.org/W2747161606","https://openalex.org/W2892356933","https://openalex.org/W2940177920","https://openalex.org/W2963045393","https://openalex.org/W2963073614","https://openalex.org/W2963082324","https://openalex.org/W2963341071","https://openalex.org/W2963420272","https://openalex.org/W2963684088","https://openalex.org/W2964207404","https://openalex.org/W3015612952","https://openalex.org/W3015785290","https://openalex.org/W3121029767","https://openalex.org/W3123318516","https://openalex.org/W4253928870","https://openalex.org/W4289665794","https://openalex.org/W6603280604","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6729966448"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W111365173","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,61],"is":[2,29],"an":[3],"essential":[4],"task":[5],"of":[6,27,64,99,113],"improving":[7],"speech":[8,21,28,46,60,102,106],"quality":[9],"in":[10,68],"noise":[11],"scenario.":[12],"Several":[13],"state-of-the-art":[14,119],"approaches":[15],"have":[16],"introduced":[17],"visual":[18,25,43,59],"information":[19,44],"for":[20,45],"enhancement,":[22,47],"since":[23],"the":[24,57,94,97,100,114],"aspect":[26],"essentially":[30],"unaffected":[31],"by":[32,48],"acoustic":[33],"environment.":[34],"This":[35],"paper":[36],"proposes":[37],"a":[38,50,72,88],"novel":[39],"framework":[40],"that":[41,74,90],"involves":[42],"incorporating":[49],"Generative":[51],"Adversarial":[52],"Network":[53],"(GAN).":[54],"In":[55],"particular,":[56],"proposed":[58,115],"GAN":[62],"consists":[63],"two":[65],"networks":[66],"trained":[67],"adversarial":[69],"manner,":[70],"i)":[71],"generator":[73],"adopts":[75],"multi-layer":[76],"feature":[77],"fusion":[78],"convolution":[79],"network":[80],"to":[81,92],"enhance":[82],"input":[83],"noisy":[84],"speech,":[85],"and":[86,104],"ii)":[87],"discriminator":[89],"attempts":[91],"minimize":[93],"discrepancy":[95],"between":[96],"distributions":[98],"clean":[101],"signal":[103],"enhanced":[105],"signal.":[107],"Experiment":[108],"results":[109],"demonstrated":[110],"superior":[111],"performance":[112],"model":[116],"against":[117],"several":[118],"models.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}