{"id":"https://openalex.org/W3014812155","doi":"https://doi.org/10.21437/interspeech.2020-1026","title":"Vocoder-Based Speech Synthesis from Silent Videos","display_name":"Vocoder-Based Speech Synthesis from Silent Videos","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3014812155","doi":"https://doi.org/10.21437/interspeech.2020-1026","mag":"3014812155"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1026","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.02541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063187524","display_name":"Daniel Michelsanti","orcid":"https://orcid.org/0000-0002-3575-1600"},"institutions":[{"id":"https://openalex.org/I4210134959","display_name":"Faculty of Design","ror":"https://ror.org/04bw0hg47","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210134959"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Daniel Michelsanti","raw_affiliation_strings":["The Technical Faculty of IT and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Technical Faculty of IT and Design","institution_ids":["https://openalex.org/I4210134959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061474153","display_name":"Olga Slizovskaia","orcid":"https://orcid.org/0000-0003-3118-5143"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Olga Slizovskaia","raw_affiliation_strings":["Pompeu Fabra Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra Univ","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077048730","display_name":"Gloria Haro","orcid":"https://orcid.org/0000-0002-8194-8092"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gloria Haro","raw_affiliation_strings":["Pompeu Fabra Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra Univ","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027977314","display_name":"Em\u00edlia G\u00f3mez","orcid":"https://orcid.org/0000-0003-4983-3989"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Emilia G\u00f3mez","raw_affiliation_strings":["Pompeu Fabra Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra Univ","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I4210115447","display_name":"Places For People","ror":"https://ror.org/036nzz613","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115447"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["AI for the People"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI for the People","institution_ids":["https://openalex.org/I4210115447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I4210115447","display_name":"Places For People","ror":"https://ror.org/036nzz613","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115447"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["AI for the People"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI for the People","institution_ids":["https://openalex.org/I4210115447"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3530","last_page":"3534"},"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":0.9983000159263611,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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":0.8014046549797058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8011679649353027},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7892476320266724},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4995553493499756},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49472925066947937},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46688809990882874},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.431379497051239},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41496390104293823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38115862011909485},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06607279181480408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014046549797058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8011679649353027},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7892476320266724},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4995553493499756},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49472925066947937},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46688809990882874},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.431379497051239},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41496390104293823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38115862011909485},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06607279181480408},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2020-1026","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.02541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.02541","pdf_url":"https://arxiv.org/pdf/2004.02541","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":"pmh:oai:pure.atira.dk:publications/05e6b04f-7cd5-4a96-8169-7b3e4dd2868d","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/05e6b04f-7cd5-4a96-8169-7b3e4dd2868d","pdf_url":"https://vbn.aau.dk/files/394278462/Open_Access_Article.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Michelsanti , D , Slizovskaia , O , Haro , G , G\u00f3mez , E , Tan , Z-H & Jensen , J 2020 , Vocoder-Based Speech Synthesis from Silent Videos . in Interspeech 2020 . Proceedings of the International Conference on Spoken Language Processing , pp. 3530-3534 , Interspeech 2020 , Shanghai , China , 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1026","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2004.02541","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.02541","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":"Preprint"},{"id":"mag:3014812155","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.02541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.02541","pdf_url":"https://arxiv.org/pdf/2004.02541","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1975079546","https://openalex.org/W1977985044","https://openalex.org/W2015143272","https://openalex.org/W2049686551","https://openalex.org/W2054139811","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2293856338","https://openalex.org/W2471520273","https://openalex.org/W2516001803","https://openalex.org/W2519648275","https://openalex.org/W2578229578","https://openalex.org/W2585824449","https://openalex.org/W2625027024","https://openalex.org/W2766812927","https://openalex.org/W2778460379","https://openalex.org/W2901997113","https://openalex.org/W2910267084","https://openalex.org/W2921904817","https://openalex.org/W2952746495","https://openalex.org/W2963019222","https://openalex.org/W2963528589","https://openalex.org/W2963807156","https://openalex.org/W2963936489","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964345931","https://openalex.org/W2964352155","https://openalex.org/W2970971581","https://openalex.org/W2972563022","https://openalex.org/W2973068670","https://openalex.org/W2979157532","https://openalex.org/W3101481642","https://openalex.org/W3104792420"],"related_works":["https://openalex.org/W3096650361","https://openalex.org/W1970171891","https://openalex.org/W2536333783","https://openalex.org/W2115066753","https://openalex.org/W3150285559","https://openalex.org/W2122366711","https://openalex.org/W3136499730","https://openalex.org/W1523214805","https://openalex.org/W2134442097","https://openalex.org/W3008480565","https://openalex.org/W2146322014","https://openalex.org/W2976747594","https://openalex.org/W2882198183","https://openalex.org/W2826861778","https://openalex.org/W2089718722","https://openalex.org/W1520114230","https://openalex.org/W1503425374","https://openalex.org/W3145885796","https://openalex.org/W171560785","https://openalex.org/W2122924390"],"abstract_inverted_index":{"Both":[0],"acoustic":[1,62],"and":[2,64,92,99,113],"visual":[3],"information":[4,86],"influence":[5],"human":[6],"perception":[7],"of":[8,15,45,109,118],"speech.":[9],"For":[10],"this":[11,32],"reason,":[12],"the":[13,42,66,116],"lack":[14],"audio":[16],"in":[17,87,102,107],"a":[18,36,46,54,69,88],"video":[19,44,59],"sequence":[20],"determines":[21],"an":[22,123],"extremely":[23],"low":[24],"speech":[25,40,67,75,101,111],"intelligibility":[26,114],"for":[27],"untrained":[28],"lip":[29],"readers.":[30],"In":[31],"paper,":[33],"we":[34],"present":[35],"way":[37],"to":[38,61,83,96],"synthesise":[39],"from":[41,57],"silent":[43],"talker":[47],"using":[48],"deep":[49],"learning.":[50],"The":[51,105],"system":[52],"learns":[53],"mapping":[55],"function":[56],"raw":[58],"frames":[60],"features":[63],"reconstructs":[65],"with":[68],"vocoder":[70],"synthesis":[71],"algorithm.":[72],"To":[73],"improve":[74],"reconstruction":[76],"performance,":[77],"our":[78,119],"model":[79],"is":[80,94],"also":[81],"trained":[82],"predict":[84],"text":[85],"multi-task":[89],"learning":[90],"fashion":[91],"it":[93],"able":[95],"simultaneously":[97],"reconstruct":[98],"recognise":[100],"real":[103],"time.":[104],"results":[106],"terms":[108],"estimated":[110],"quality":[112],"show":[115],"effectiveness":[117],"method,":[120],"which":[121],"exhibits":[122],"improvement":[124],"over":[125],"existing":[126],"video-to-speech":[127],"approaches.":[128]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}