{"id":"https://openalex.org/W2951804919","doi":"https://doi.org/10.21437/interspeech.2019-1445","title":"Video-Driven Speech Reconstruction Using Generative Adversarial Networks","display_name":"Video-Driven Speech Reconstruction Using Generative Adversarial Networks","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2951804919","doi":"https://doi.org/10.21437/interspeech.2019-1445","mag":"2951804919"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.06301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079503255","display_name":"Konstantinos Vougioukas","orcid":"https://orcid.org/0000-0001-8552-5559"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Konstantinos Vougioukas","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Samsung (South Korea), Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung (South Korea), Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079503255"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.167,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43231893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4125","last_page":"4129"},"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":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.839061975479126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7157283425331116},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5317990183830261},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45514822006225586},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.44109925627708435},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.43179967999458313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42677462100982666},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.41795966029167175},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38437652587890625},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.33771103620529175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839061975479126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7157283425331116},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5317990183830261},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45514822006225586},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.44109925627708435},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.43179967999458313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42677462100982666},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.41795966029167175},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38437652587890625},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.33771103620529175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-1445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.06301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06301","pdf_url":"https://arxiv.org/pdf/1906.06301","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2951804919","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1906.06301","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/77510","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/77510","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2019","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1906.06301","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.06301","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.06301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06301","pdf_url":"https://arxiv.org/pdf/1906.06301","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1591978968","display_name":null,"funder_award_id":"2130174","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5321982477","display_name":null,"funder_award_id":"Titan V GPU","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951804919.pdf","grobid_xml":"https://content.openalex.org/works/W2951804919.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W2054139811","https://openalex.org/W2107860279","https://openalex.org/W2293856338","https://openalex.org/W2578229578","https://openalex.org/W2585824449","https://openalex.org/W2604379605","https://openalex.org/W2625027024","https://openalex.org/W2739748921","https://openalex.org/W2910267084","https://openalex.org/W2952746495","https://openalex.org/W2962879692","https://openalex.org/W2963019222","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2964095416","https://openalex.org/W2964352155"],"related_works":["https://openalex.org/W2972563022","https://openalex.org/W3163320179","https://openalex.org/W594764791","https://openalex.org/W2809767522","https://openalex.org/W3034514362","https://openalex.org/W3040260790","https://openalex.org/W3128798311","https://openalex.org/W2786254735","https://openalex.org/W3119219688","https://openalex.org/W3196698946","https://openalex.org/W3115250497","https://openalex.org/W3191488649","https://openalex.org/W2105332826","https://openalex.org/W2964404767","https://openalex.org/W2740883964","https://openalex.org/W2963288440","https://openalex.org/W3213458023","https://openalex.org/W2752161456","https://openalex.org/W3035585190","https://openalex.org/W2741633070"],"abstract_inverted_index":{"Speech":[0],"is":[1,58,67,77,98],"a":[2],"means":[3],"of":[4,16,26,38,60,74,94,139],"communication":[5],"which":[6,66],"relies":[7],"on":[8,56,79,118,130,136],"both":[9,84],"audio":[10,41,108,126],"and":[11,87,109],"visual":[12],"information.":[13,27],"The":[14,72],"absence":[15],"one":[17],"modality":[18],"can":[19],"often":[20],"lead":[21],"to":[22,47,106,112],"confusion":[23],"or":[24],"misinterpretation":[25],"In":[28],"this":[29,97],"paper":[30],"we":[31],"present":[32],"an":[33],"end-to-end":[34],"temporal":[35],"model":[36,76],"capable":[37,59],"directly":[39,105],"synthesising":[40],"from":[42],"silent":[43],"video,":[44],"without":[45],"needing":[46],"transform":[48],"to-and-from":[49],"intermediate":[50],"features.":[51],"Our":[52],"proposed":[53],"approach,":[54],"based":[55,129],"GANs":[57],"producing":[61],"natural":[62],"sounding,":[63],"intelligible":[64,114],"speech":[65,115],"synchronised":[68],"with":[69],"the":[70,80,92,99,110,124,131,137,140],"video.":[71],"performance":[73],"our":[75,95],"evaluated":[78],"GRID":[81],"dataset":[82],"for":[83],"speaker":[85,88],"dependent":[86],"independent":[89],"scenarios.":[90],"To":[91],"best":[93],"knowledge":[96],"first":[100,111],"method":[101],"that":[102],"maps":[103],"video":[104],"raw":[107],"produce":[113],"when":[116],"tested":[117],"previously":[119],"unseen":[120],"speakers.":[121],"We":[122],"evaluate":[123],"synthesised":[125],"not":[127],"only":[128],"sound":[132],"quality":[133],"but":[134],"also":[135],"accuracy":[138],"spoken":[141],"words.":[142]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}