{"id":"https://openalex.org/W2794908863","doi":"https://doi.org/10.21437/interspeech.2018-1955","title":"Visual Speech Enhancement","display_name":"Visual Speech Enhancement","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2794908863","doi":"https://doi.org/10.21437/interspeech.2018-1955","mag":"2794908863"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1955","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1955","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/1711.08789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041453029","display_name":"Aviv Gabbay","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Aviv Gabbay","raw_affiliation_strings":["Hebrew University of Jerusalem, Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061624399","display_name":"Asaph Shamir","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Asaph Shamir","raw_affiliation_strings":["Hebrew University of Jerusalem, Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045004853","display_name":"Bezalel Peleg","orcid":"https://orcid.org/0000-0002-4468-2619"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shmuel Peleg","raw_affiliation_strings":["Hebrew University of Jerusalem, Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041453029"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02612501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1170","last_page":"1174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T11448","display_name":"Face recognition and analysis","score":0.9606000185012817,"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":0.8151249885559082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7353993654251099},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6222640872001648},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5669141411781311},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5221405625343323},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5086179971694946},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5006179809570312},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4507546126842499},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43076297640800476},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.42750129103660583},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42153507471084595},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40991637110710144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3893277049064636},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.317266583442688},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20926272869110107},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19829994440078735},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14800435304641724},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.059727996587753296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151249885559082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7353993654251099},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6222640872001648},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5669141411781311},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5221405625343323},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5086179971694946},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5006179809570312},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4507546126842499},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43076297640800476},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.42750129103660583},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42153507471084595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40991637110710144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3893277049064636},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.317266583442688},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20926272869110107},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19829994440078735},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14800435304641724},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.059727996587753296},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-1955","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1955","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:1711.08789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.08789","pdf_url":"https://arxiv.org/pdf/1711.08789","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2794908863","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.08789v3","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.1711.08789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.08789","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:1711.08789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.08789","pdf_url":"https://arxiv.org/pdf/1711.08789","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2794908863.pdf","grobid_xml":"https://content.openalex.org/works/W2794908863.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963082324","https://openalex.org/W2750143381","https://openalex.org/W2964207404","https://openalex.org/W2141769559","https://openalex.org/W2797032258","https://openalex.org/W3004146833","https://openalex.org/W2997382144","https://openalex.org/W3121029767","https://openalex.org/W111284038","https://openalex.org/W2577762507","https://openalex.org/W2958646611","https://openalex.org/W3015445830","https://openalex.org/W2525694994","https://openalex.org/W3182657421","https://openalex.org/W3160672713","https://openalex.org/W2039679570","https://openalex.org/W2959214850","https://openalex.org/W2987346570","https://openalex.org/W2572763611","https://openalex.org/W182561118"],"abstract_inverted_index":{"When":[0],"video":[1,15],"is":[2,36,73,116],"shot":[3],"in":[4,13,51],"noisy":[5],"environment,":[6],"the":[7,14,20,52,60,63,70,78,87,92,118,132],"voice":[8,61,79],"of":[9,62,80,135],"a":[10,81,124],"speaker":[11,65,82],"seen":[12],"can":[16],"be":[17,121],"enhanced":[18],"using":[19],"visible":[21],"mouth":[22],"movements,":[23],"reducing":[24],"background":[25,67],"noise.":[26,68],"While":[27],"most":[28],"existing":[29],"methods":[30,109],"use":[31],"audio-only":[32],"inputs,":[33],"improved":[34],"performance":[35],"obtained":[37],"with":[38],"our":[39],"visual":[40,93,108],"speech":[41],"enhancement,":[42],"based":[43],"on":[44,110,123],"an":[45],"audio-visual":[46],"neural":[47],"network.":[48],"We":[49],"include":[50],"training":[53],"data":[54],"videos":[55],"to":[56,76,98,120],"which":[57],"we":[58],"added":[59],"target":[64],"as":[66,131],"Since":[69],"audio":[71,107],"input":[72,94],"not":[74,126],"sufficient":[75],"separate":[77],"from":[83],"his":[84],"own":[85],"voice,":[86],"trained":[88],"model":[89,104],"better":[90],"exploits":[91],"and":[95],"generalizes":[96],"well":[97],"different":[99],"noise":[100],"types.":[101],"The":[102],"proposed":[103],"outperforms":[105],"prior":[106],"two":[111],"public":[112],"lipreading":[113],"datasets.":[114],"It":[115],"also":[117],"first":[119],"demonstrated":[122],"dataset":[125],"designed":[127],"for":[128],"lipreading,":[129],"such":[130],"weekly":[133],"addresses":[134],"Barack":[136],"Obama.":[137]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}