{"id":"https://openalex.org/W4224916651","doi":"https://doi.org/10.1109/icassp43922.2022.9747559","title":"Learning to Predict Speech in Silent Videos Via Audiovisual Analogy","display_name":"Learning to Predict Speech in Silent Videos Via Audiovisual Analogy","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916651","doi":"https://doi.org/10.1109/icassp43922.2022.9747559"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747559","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010648323","display_name":"Ravindra Yadav","orcid":"https://orcid.org/0000-0003-4628-0688"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ravindra Yadav","raw_affiliation_strings":["Indian Institute of Technology Kanpur,India","Indian Institute of Technology Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur,India","institution_ids":["https://openalex.org/I94234084"]},{"raw_affiliation_string":"Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083439972","display_name":"Ashish Sardana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Sardana","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinay P Namboodiri","raw_affiliation_strings":["University of Bath,UK","University of Bath, UK"],"affiliations":[{"raw_affiliation_string":"University of Bath,UK","institution_ids":["https://openalex.org/I51601045"]},{"raw_affiliation_string":"University of Bath, UK","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085503354","display_name":"Rajesh M. Hegde","orcid":"https://orcid.org/0000-0002-6142-7724"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajesh M Hegde","raw_affiliation_strings":["Indian Institute of Technology Kanpur,India","Indian Institute of Technology Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur,India","institution_ids":["https://openalex.org/I94234084"]},{"raw_affiliation_string":"Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010648323"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.46919431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8042","last_page":"8046"},"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":0.9983000159263611,"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":0.9932000041007996,"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":0.8378455638885498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6964976787567139},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6526644229888916},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.5986490845680237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5411279797554016},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48784422874450684},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48743513226509094},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48657286167144775},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4620155394077301},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4278390407562256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36692774295806885},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.24922966957092285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378455638885498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6964976787567139},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6526644229888916},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.5986490845680237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411279797554016},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48784422874450684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48743513226509094},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48657286167144775},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4620155394077301},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4278390407562256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36692774295806885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.24922966957092285},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747559","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G487895436","display_name":null,"funder_award_id":"EP/T022523/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5212373428","display_name":null,"funder_award_id":"EP/M023281/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2015143272","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2130942839","https://openalex.org/W2184218725","https://openalex.org/W2293856338","https://openalex.org/W2516001803","https://openalex.org/W2585824449","https://openalex.org/W2625027024","https://openalex.org/W2785325870","https://openalex.org/W2896457183","https://openalex.org/W2949662773","https://openalex.org/W2963019222","https://openalex.org/W2964243274","https://openalex.org/W2964352155","https://openalex.org/W2972563022","https://openalex.org/W3035626590","https://openalex.org/W3104792420","https://openalex.org/W3160305627","https://openalex.org/W4320013936","https://openalex.org/W6679436768","https://openalex.org/W6686131816","https://openalex.org/W6785417915"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3205835383","https://openalex.org/W2987365737","https://openalex.org/W4213149867","https://openalex.org/W3100270142","https://openalex.org/W2348497393","https://openalex.org/W2165444838","https://openalex.org/W2793122029","https://openalex.org/W1516751421","https://openalex.org/W2399226626"],"abstract_inverted_index":{"Lipreading":[0],"is":[1,54,126],"a":[2,19,28,57,67,76,85,97,134,148],"difficult":[3],"task,":[4],"even":[5,18],"for":[6,100],"humans.":[7],"And":[8],"synthesizing":[9],"the":[10,39,42,63,81,103,107,119,129,158,165,189],"original":[11],"speech":[12,64,77,131,192],"waveform":[13],"from":[14,102],"lipreading":[15],"makes":[16],"it":[17,112],"more":[20,184],"challenging":[21],"problem.":[22],"Towards":[23],"this":[24,50],"end,":[25],"we":[26,110],"present":[27],"deep":[29,135],"learning":[30,116],"framework":[31,74],"that":[32,59,95,164,179],"can":[33,60],"be":[34],"trained":[35],"end-to-end":[36],"to":[37,55,106,128],"learn":[38],"mapping":[40,80],"between":[41,118],"auditory":[43],"and":[44,155,186],"visual":[45],"signals.":[46],"In":[47,122],"particular,":[48],"in":[49,66,84],"paper,":[51],"our":[52,180],"interest":[53],"design":[56],"model":[58],"efficiently":[61],"predict":[62,140],"signal":[65,78],"given":[68],"silent":[69],"talking-face":[70],"video.":[71],"The":[72],"proposed":[73,166],"generates":[75],"by":[79,144],"video":[82],"frames":[83],"sequence":[86],"of":[87],"feature":[88],"vectors.":[89],"However,":[90],"unlike":[91],"some":[92],"recent":[93],"methods":[94],"adopt":[96],"sequence-to-sequence":[98],"approach":[99],"translation":[101],"frame":[104,125],"stream":[105,143],"audio":[108,142],"stream,":[109],"posit":[111],"as":[113],"an":[114],"analogy":[115,137],"problem":[117],"two":[120],"modalities.":[121],"which":[123],"each":[124],"mapped":[127],"corresponding":[130],"segment":[132],"via":[133],"audio-visual":[136],"framework.":[138],"We":[139],"plausible":[141],"training":[145],"adversarially":[146],"against":[147],"discriminator":[149],"network.":[150],"Our":[151,175],"experiments,":[152],"both":[153],"qualitative":[154],"quantitative,":[156],"on":[157,171],"publicly":[159],"available":[160],"GRID":[161],"dataset":[162],"show":[163],"method":[167],"outperforms":[168],"prior":[169],"work":[170],"existing":[172],"evaluation":[173],"benchmarks.":[174],"user":[176],"studies":[177],"confirm":[178],"generated":[181],"samples":[182],"are":[183],"natural":[185],"closely":[187],"match":[188],"ground":[190],"truth":[191],"signal.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}