{"id":"https://openalex.org/W2797090057","doi":"https://doi.org/10.21437/interspeech.2018-1400","title":"The Conversation: Deep Audio-Visual Speech Enhancement","display_name":"The Conversation: Deep Audio-Visual Speech Enhancement","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2797090057","doi":"https://doi.org/10.21437/interspeech.2018-1400","mag":"2797090057"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1400","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/1804.04121","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, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","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, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","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, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","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":6.4668,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97398882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3244","last_page":"3248"},"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":0.9945999979972839,"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":0.9926999807357788,"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/conversation","display_name":"Conversation","score":0.7867710590362549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744022786617279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7240459322929382},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6090101599693298},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5076380968093872},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4357723295688629},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.428555428981781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711729049682617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3262137770652771},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2178587019443512},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.208683043718338},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.18488487601280212},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12246078252792358}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7867710590362549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744022786617279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7240459322929382},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6090101599693298},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5076380968093872},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4357723295688629},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.428555428981781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711729049682617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3262137770652771},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2178587019443512},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.208683043718338},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.18488487601280212},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12246078252792358},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-1400","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.04121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.04121","pdf_url":"https://arxiv.org/pdf/1804.04121","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":null},{"id":"mag:2797090057","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1804.04121","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.1804.04121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.04121","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:1804.04121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.04121","pdf_url":"https://arxiv.org/pdf/1804.04121","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":null},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"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"}],"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/W2797090057.pdf","grobid_xml":"https://content.openalex.org/works/W2797090057.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1552314771","https://openalex.org/W1573024203","https://openalex.org/W1664049007","https://openalex.org/W2018840451","https://openalex.org/W2038010270","https://openalex.org/W2099128937","https://openalex.org/W2105921478","https://openalex.org/W2111070087","https://openalex.org/W2119901478","https://openalex.org/W2122982914","https://openalex.org/W2128653983","https://openalex.org/W2141998673","https://openalex.org/W2154151281","https://openalex.org/W2167734090","https://openalex.org/W2194775991","https://openalex.org/W2278884322","https://openalex.org/W2302255633","https://openalex.org/W2398813462","https://openalex.org/W2406737436","https://openalex.org/W2407692257","https://openalex.org/W2515334659","https://openalex.org/W2531409750","https://openalex.org/W2578229578","https://openalex.org/W2594690981","https://openalex.org/W2596627958","https://openalex.org/W2604379605","https://openalex.org/W2744766693","https://openalex.org/W2749131051","https://openalex.org/W2766712974","https://openalex.org/W2767108501","https://openalex.org/W2787944098","https://openalex.org/W2788241093","https://openalex.org/W2797032258","https://openalex.org/W2952746495","https://openalex.org/W2962960500"],"related_works":["https://openalex.org/W2964171275","https://openalex.org/W3123318516","https://openalex.org/W2194775991","https://openalex.org/W2594690981","https://openalex.org/W2952746495","https://openalex.org/W2604379605","https://openalex.org/W2221409856","https://openalex.org/W2015143272","https://openalex.org/W1522301498","https://openalex.org/W2962960500","https://openalex.org/W2962865004","https://openalex.org/W2460742184","https://openalex.org/W2184188583","https://openalex.org/W2963082324","https://openalex.org/W2808631503","https://openalex.org/W2619947201","https://openalex.org/W2029199293","https://openalex.org/W2738406145","https://openalex.org/W2593116425","https://openalex.org/W1901129140"],"abstract_inverted_index":{"Our":[0],"goal":[1],"is":[2,43,71],"to":[3,22,45,73],"isolate":[4],"individual":[5],"speakers":[6,27,74],"from":[7,25],"multi-talker":[8],"simultaneous":[9],"speech":[10,39],"in":[11,15,28,53],"videos.":[12],"Existing":[13],"works":[14],"this":[16,32],"area":[17],"have":[18],"focussed":[19],"on":[20],"trying":[21],"separate":[23,46],"utterances":[24],"known":[26],"controlled":[29],"environments.":[30,83],"In":[31],"paper,":[33],"we":[34],"propose":[35],"a":[36,47],"deep":[37],"audio-visual":[38],"enhancement":[40],"network":[41],"that":[42],"able":[44],"speaker's":[48],"voice":[49],"given":[50],"lip":[51],"regions":[52],"the":[54,60,63,66],"corresponding":[55],"video,":[56],"by":[57],"predicting":[58],"both":[59],"magnitude":[61],"and":[62,76,80,88],"phase":[64],"of":[65],"target":[67],"signal.":[68],"The":[69],"method":[70],"applicable":[72],"unheard":[75],"unseen":[77],"during":[78],"training,":[79],"for":[81],"unconstrained":[82],"We":[84],"demonstrate":[85],"strong":[86],"quantitative":[87],"qualitative":[89],"results,":[90],"isolating":[91],"extremely":[92],"challenging":[93],"real-world":[94],"examples.":[95]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}