{"id":"https://openalex.org/W4296069328","doi":"https://doi.org/10.21437/interspeech.2022-10770","title":"SVTS: Scalable Video-to-Speech Synthesis","display_name":"SVTS: Scalable Video-to-Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069328","doi":"https://doi.org/10.21437/interspeech.2022-10770"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10770","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10770","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/99292/99292 schoburgcarrillodemira22_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013092421","display_name":"Rodrigo Mira","orcid":"https://orcid.org/0000-0002-9493-3842"},"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":"Rodrigo Schoburg Carrillo de Mira","raw_affiliation_strings":["Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010477883","display_name":"Alexandros Haliassos","orcid":"https://orcid.org/0000-0001-8856-5193"},"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":"Alexandros Haliassos","raw_affiliation_strings":["Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","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, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"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":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Imperial College London, UK","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/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":"Maja Pantic","raw_affiliation_strings":["Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1377,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9381103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1836","last_page":"1840"},"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":0.9980999827384949,"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":0.9923999905586243,"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/spectrogram","display_name":"Spectrogram","score":0.9133419990539551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8511158227920532},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6928372383117676},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5293102264404297},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.476335346698761},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46753570437431335},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4429301619529724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43868398666381836},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4140964150428772}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9133419990539551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511158227920532},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6928372383117676},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5293102264404297},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.476335346698761},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46753570437431335},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4429301619529724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43868398666381836},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4140964150428772},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10770","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10770","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:99292","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-992925","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/99292/99292 schoburgcarrillodemira22_interspeech.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conferenceobject"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:99292","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-992925","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/99292/99292 schoburgcarrillodemira22_interspeech.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conferenceobject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296069328.pdf","grobid_xml":"https://content.openalex.org/works/W4296069328.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2029199293","https://openalex.org/W2120847449","https://openalex.org/W2141998673","https://openalex.org/W2152859600","https://openalex.org/W2194775991","https://openalex.org/W2293856338","https://openalex.org/W2519091744","https://openalex.org/W2550980560","https://openalex.org/W2585824449","https://openalex.org/W2625027024","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2949662773","https://openalex.org/W2963019222","https://openalex.org/W2963263347","https://openalex.org/W2963654155","https://openalex.org/W2964243274","https://openalex.org/W2964352155","https://openalex.org/W2972359262","https://openalex.org/W2972563022","https://openalex.org/W3015338123","https://openalex.org/W3034552680","https://openalex.org/W3035626590","https://openalex.org/W3096650361","https://openalex.org/W3097777922","https://openalex.org/W3144035034","https://openalex.org/W3160305627","https://openalex.org/W3161236344","https://openalex.org/W3162293946","https://openalex.org/W3211862173","https://openalex.org/W3213322812","https://openalex.org/W4206204999","https://openalex.org/W4220782092","https://openalex.org/W4221153068"],"related_works":["https://openalex.org/W4397292310","https://openalex.org/W2500421879","https://openalex.org/W2537969829","https://openalex.org/W2184371793","https://openalex.org/W2186688931","https://openalex.org/W4205598694","https://openalex.org/W2389032213","https://openalex.org/W2356192947","https://openalex.org/W4391272374","https://openalex.org/W2371908859"],"abstract_inverted_index":{"Video-to-speech":[0],"synthesis":[1],"(also":[2],"known":[3],"as":[4],"lip-to-speech)":[5],"refers":[6],"to":[7,28,60,134,150],"the":[8,15,41,94,141,148,155],"translation":[9],"of":[10,25,44,81,143],"silent":[11],"lip":[12],"movements":[13],"into":[14,97],"corresponding":[16],"audio.":[17,99],"This":[18],"task":[19],"has":[20],"received":[21],"an":[22],"increasing":[23],"amount":[24],"attention":[26],"due":[27],"its":[29],"self-supervised":[30],"nature":[31],"(i.e.,":[32],"can":[33,127],"be":[34],"trained":[35],"without":[36],"manual":[37],"labelling)":[38],"combined":[39],"with":[40,63],"ever-growing":[42],"collection":[43],"audio-visual":[45],"data":[46],"available":[47],"online.":[48],"Despite":[49],"these":[50],"strong":[51],"motivations,":[52],"contemporary":[53],"video-to-speech":[54,78],"works":[55],"focus":[56],"mainly":[57],"on":[58,112,118,154],"small-":[59],"medium-sized":[61],"corpora":[62],"substantial":[64],"constraints":[65],"in":[66],"both":[67],"vocabulary":[68],"and":[69,87,107,129,137],"setting.":[70],"In":[71],"this":[72],"work,":[73],"we":[74,126,146],"introduce":[75],"a":[76,84,88,122],"scalable":[77],"framework":[79],"consisting":[80],"two":[82],"components:":[83],"video-to-spectrogram":[85],"predictor":[86],"pre-trained":[89],"neural":[90],"vocoder,":[91],"which":[92],"converts":[93],"mel-frequency":[95],"spectrograms":[96],"waveform":[98],"We":[100],"achieve":[101],"state-of-the":[102],"art":[103],"results":[104,153],"for":[105],"GRID":[106],"considerably":[108],"outperform":[109],"previous":[110],"approaches":[111],"LRW.":[113],"More":[114],"importantly,":[115],"by":[116],"focusing":[117],"spectrogram":[119],"prediction":[120],"using":[121],"simple":[123],"feedforward":[124],"model,":[125],"efficiently":[128],"effectively":[130],"scale":[131],"our":[132,144],"method":[133],"very":[135],"large":[136],"unconstrained":[138],"datasets:":[139],"To":[140],"best":[142],"knowledge,":[145],"are":[147],"first":[149],"show":[151],"intelligible":[152],"challenging":[156],"LRS3":[157],"dataset.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-09-17T00:00:00"}