{"id":"https://openalex.org/W3000256674","doi":"https://doi.org/10.1109/icassp40776.2020.9053415","title":"Visually Guided Self Supervised Learning of Speech Representations","display_name":"Visually Guided Self Supervised Learning of Speech Representations","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3000256674","doi":"https://doi.org/10.1109/icassp40776.2020.9053415","mag":"3000256674"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2001.04316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102760892","display_name":"Abhinav Shukla","orcid":"https://orcid.org/0000-0003-4030-962X"},"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":true,"raw_author_name":"Abhinav Shukla","raw_affiliation_strings":["Imperial College, London, UK","Imperial College (London, UK)"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College (London, UK)","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079503255","display_name":"Konstantinos Vougioukas","orcid":"https://orcid.org/0000-0001-8552-5559"},"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":"Konstantinos Vougioukas","raw_affiliation_strings":["Imperial College, London, UK","Imperial College (London, UK)"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College (London, UK)","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"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":"Pingchuan Ma","raw_affiliation_strings":["Imperial College, London, UK","Imperial College (London, UK)"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"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","Imperial College (London, UK)"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"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","Imperial College (London, UK)"],"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College (London, UK)","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102760892"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.3043,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51048997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6299","last_page":"6303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9850000143051147,"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":0.7836363315582275},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6360853314399719},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6151853799819946},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6114596724510193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.583940327167511},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5386109352111816},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5159810185432434},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4937973916530609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4846575856208801},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44844773411750793},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41765278577804565},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4172891080379486},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41509196162223816},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21098214387893677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836363315582275},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6360853314399719},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6151853799819946},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6114596724510193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.583940327167511},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5386109352111816},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5159810185432434},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4937973916530609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846575856208801},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44844773411750793},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41765278577804565},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4172891080379486},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41509196162223816},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21098214387893677},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.04316","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04316","pdf_url":"https://arxiv.org/pdf/2001.04316","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":"mag:3000256674","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.04316.pdf","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":"pmh:oai:spiral.imperial.ac.uk:10044/1/76974","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/76974","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working Paper"},{"id":"doi:10.48550/arxiv.2001.04316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.04316","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"},{"id":"doi:10.17023/axt3-vr24","is_oa":true,"landing_page_url":"https://doi.org/10.17023/axt3-vr24","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"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:2001.04316","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04316","pdf_url":"https://arxiv.org/pdf/2001.04316","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","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1591978968","display_name":null,"funder_award_id":"2130174","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5321982477","display_name":null,"funder_award_id":"Titan V GPU","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3000256674.pdf","grobid_xml":"https://content.openalex.org/works/W3000256674.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1901129140","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2030931454","https://openalex.org/W2261706002","https://openalex.org/W2550462002","https://openalex.org/W2594690981","https://openalex.org/W2787560479","https://openalex.org/W2796992393","https://openalex.org/W2797583228","https://openalex.org/W2803193013","https://openalex.org/W2804600264","https://openalex.org/W2842511635","https://openalex.org/W2902368158","https://openalex.org/W2926827382","https://openalex.org/W2935542736","https://openalex.org/W2947454875","https://openalex.org/W2962742544","https://openalex.org/W2962780374","https://openalex.org/W2962931510","https://openalex.org/W2962969419","https://openalex.org/W2963115079","https://openalex.org/W2963341956","https://openalex.org/W2964048159","https://openalex.org/W2973049979","https://openalex.org/W6611801654","https://openalex.org/W6639824700","https://openalex.org/W6692642783","https://openalex.org/W6734491695","https://openalex.org/W6747045456","https://openalex.org/W6754048563"],"related_works":["https://openalex.org/W3015356123","https://openalex.org/W3040260790","https://openalex.org/W3022984097","https://openalex.org/W3173388686","https://openalex.org/W3123226376","https://openalex.org/W3032892481","https://openalex.org/W3094123278","https://openalex.org/W3172355142","https://openalex.org/W3093456287","https://openalex.org/W3017923487","https://openalex.org/W3099638501","https://openalex.org/W2608612081","https://openalex.org/W2972463723","https://openalex.org/W2740883964","https://openalex.org/W3021378543","https://openalex.org/W3205239183","https://openalex.org/W2809767522","https://openalex.org/W3162391496","https://openalex.org/W3201143670","https://openalex.org/W3159929162"],"abstract_inverted_index":{"Self":[0],"supervised":[1,49],"representation":[2],"learning":[3,47,56,153,162],"has":[4,33,164],"recently":[5],"attracted":[6],"a":[7,25,53,72,81,86,157,178,191],"lot":[8],"of":[9,67,105,132,149,182,185,194],"research":[10],"interest":[11],"for":[12,46,55,136,142,152,160],"both":[13],"the":[14,40,43,61,65,92,102,106,112,133,147,169],"audio":[15,57,88,113,154,174],"and":[16,31,90,126,139,189],"visual":[17,62,150],"modalities.":[18],"However,":[19],"most":[20],"works":[21],"typically":[22],"focus":[23],"on":[24,123],"particular":[26],"modality":[27,63],"or":[28],"feature":[29],"alone":[30],"there":[32],"been":[34,166],"very":[35],"limited":[36],"work":[37],"that":[38,120],"studies":[39],"interaction":[41],"between":[42],"two":[44],"modalities":[45],"self":[48],"representations.":[50],"We":[51,70,129],"propose":[52],"framework":[54],"representations":[58,119,155],"guided":[59],"by":[60],"in":[64,77,168],"context":[66],"audiovisual":[68,187],"speech.":[69],"employ":[71],"generative":[73],"audio-to-video":[74],"training":[75,183],"scheme":[76],"which":[78,163],"we":[79,121],"animate":[80],"still":[82],"image":[83],"corresponding":[84],"to":[85,95,101],"given":[87],"clip":[89],"optimize":[91],"generated":[93],"video":[94,104],"be":[96],"as":[97,99,156],"close":[98],"possible":[100],"real":[103],"speech":[107,118,127,143,188],"segment.":[108],"Through":[109],"this":[110],"process,":[111],"encoder":[114],"network":[115],"learns":[116],"useful":[117],"evaluate":[122],"emotion":[124,137],"recognition":[125,138],"recognition.":[128,144],"achieve":[130],"state":[131],"art":[134],"results":[135,141],"competitive":[140],"This":[145],"demonstrates":[146],"potential":[148],"supervision":[151],"novel":[158],"way":[159],"self-supervised":[161],"not":[165],"explored":[167],"past.":[170],"The":[171],"proposed":[172],"unsupervised":[173],"features":[175],"can":[176],"leverage":[177],"virtually":[179],"unlimited":[180],"amount":[181],"data":[184],"unlabelled":[186],"have":[190],"large":[192],"number":[193],"potentially":[195],"promising":[196],"applications.":[197]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
