{"id":"https://openalex.org/W2956679704","doi":"https://doi.org/10.21437/interspeech.2019-3114","title":"My Lips Are Concealed: Audio-Visual Speech Enhancement Through Obstructions","display_name":"My Lips Are Concealed: Audio-Visual Speech Enhancement Through Obstructions","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2956679704","doi":"https://doi.org/10.21437/interspeech.2019-3114","mag":"2956679704"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3114","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3114","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/1907.04975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018690028","display_name":"Triantafyllos Afouras","orcid":"https://orcid.org/0000-0002-3935-9681"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Triantafyllos Afouras","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018690028"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":2.0038,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87250487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4295","last_page":"4299"},"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":0.9973999857902527,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6761289238929749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6709997653961182},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6527032852172852},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6221094131469727},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6087055802345276},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.4137450158596039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3607795238494873},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1358666718006134}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6761289238929749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6709997653961182},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6527032852172852},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6221094131469727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6087055802345276},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.4137450158596039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3607795238494873},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1358666718006134},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-3114","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3114","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:1907.04975","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04975","pdf_url":"https://arxiv.org/pdf/1907.04975","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":null,"raw_type":"text"},{"id":"mag:2956679704","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.04975","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":"doi:10.48550/arxiv.1907.04975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.04975","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:1907.04975","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04975","pdf_url":"https://arxiv.org/pdf/1907.04975","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2018133609","display_name":"Seebibyte: Visual Search for the Era of Big Data","funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8416736120","display_name":null,"funder_award_id":"Seebibyte EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"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/W2956679704.pdf","grobid_xml":"https://content.openalex.org/works/W2956679704.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1573024203","https://openalex.org/W2038010270","https://openalex.org/W2099128937","https://openalex.org/W2111070087","https://openalex.org/W2119901478","https://openalex.org/W2122982914","https://openalex.org/W2154151281","https://openalex.org/W2167734090","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2407692257","https://openalex.org/W2460742184","https://openalex.org/W2771039075","https://openalex.org/W2788241093","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2893436174","https://openalex.org/W2962866211","https://openalex.org/W2962960500","https://openalex.org/W2963528589","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2973062255","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W2972513594","https://openalex.org/W3123318516","https://openalex.org/W2963082324","https://openalex.org/W2962960500","https://openalex.org/W2808631503","https://openalex.org/W2797090057","https://openalex.org/W2221409856","https://openalex.org/W1531976713","https://openalex.org/W2558728505","https://openalex.org/W2094800907","https://openalex.org/W2612434330","https://openalex.org/W2112043905","https://openalex.org/W3024147341","https://openalex.org/W2194775991","https://openalex.org/W2864706727","https://openalex.org/W3198690170","https://openalex.org/W2293401412","https://openalex.org/W2039562357","https://openalex.org/W2002591764","https://openalex.org/W2800753652"],"abstract_inverted_index":{"Our":[0],"objective":[1],"is":[2,53,100,123],"an":[3],"audio-visual":[4,48],"model":[5,99],"for":[6,148],"separating":[7],"a":[8,12,46,57,69],"single":[9],"speaker":[10,29],"from":[11,119],"mixture":[13],"of":[14,71,132,150],"sounds":[15],"such":[16],"as":[17],"other":[18],"speakers":[19,133],"and":[20,105,125],"background":[21],"noise.":[22],"Moreover,":[23],"we":[24,44,126],"wish":[25],"to":[26,39,55],"hear":[27],"the":[28,32,64,90,111,116,153],"even":[30],"when":[31],"visual":[33,96,117,154],"cues":[34],"are":[35],"temporarily":[36],"absent":[37],"due":[38],"occlusion.":[40],"To":[41],"this":[42],"end":[43],"introduce":[45],"deep":[47],"speech":[49],"enhancement":[50],"network":[51],"that":[52,114],"able":[54],"separate":[56],"speaker's":[58,65],"voice":[59,75],"by":[60,80,86,102,106],"conditioning":[61],"on":[62,129],"both":[63],"lip":[66],"movements":[67],"and/or":[68],"representation":[70,76,91],"their":[72],"voice.":[73],"The":[74,98,121,139],"can":[77],"be":[78],"obtained":[79],"either":[81],"(i)":[82],"enrollment,":[83],"or":[84],"(ii)":[85],"self-enrollment":[87],"--":[88],"learning":[89],"on-the-fly":[92],"given":[93],"sufficient":[94],"unobstructed":[95],"input.":[97],"trained":[101],"blending":[103],"audios,":[104],"introducing":[107],"artificial":[108],"occlusions":[109],"around":[110],"mouth":[112],"region":[113],"prevent":[115],"modality":[118],"dominating.":[120],"method":[122,140],"speaker-independent,":[124],"demonstrate":[127],"it":[128],"real":[130],"examples":[131],"unheard":[134],"(and":[135],"unseen)":[136],"during":[137],"training.":[138],"also":[141],"improves":[142],"over":[143],"previous":[144],"models":[145],"in":[146,152],"particular":[147],"cases":[149],"occlusion":[151],"modality.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
