{"id":"https://openalex.org/W3213322812","doi":"https://doi.org/10.1109/taslp.2021.3126925","title":"Speech Reconstruction With Reminiscent Sound Via Visual Voice Memory","display_name":"Speech Reconstruction With Reminiscent Sound Via Visual Voice Memory","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3213322812","doi":"https://doi.org/10.1109/taslp.2021.3126925","mag":"3213322812"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3126925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3126925","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5067120705","display_name":"Joanna Hong","orcid":"https://orcid.org/0000-0003-4182-1000"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joanna Hong","raw_affiliation_strings":["Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Korea (the Republic of), 34141 (e-mail: joanna2587@kaist.ac.kr)"],"raw_orcid":"https://orcid.org/0000-0003-4182-1000","affiliations":[{"raw_affiliation_string":"Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Korea (the Republic of), 34141 (e-mail: joanna2587@kaist.ac.kr)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Korea (the Republic of), 34141 (e-mail: ms.k@kaist.ac.kr)"],"raw_orcid":"https://orcid.org/0000-0002-6514-0018","affiliations":[{"raw_affiliation_string":"Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Korea (the Republic of), 34141 (e-mail: ms.k@kaist.ac.kr)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376688","display_name":"Se Jin Park","orcid":"https://orcid.org/0000-0001-8467-3576"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se Jin Park","raw_affiliation_strings":["Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Korea (the Republic of), 34141 (e-mail: jinny960812@kaist.ac.kr)"],"raw_orcid":"https://orcid.org/0000-0001-8467-3576","affiliations":[{"raw_affiliation_string":"Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Korea (the Republic of), 34141 (e-mail: jinny960812@kaist.ac.kr)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, 34968 Daejeon, Daejeon, Korea (the Republic of), (e-mail: ymro@kaist.ac.kr)"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, 34968 Daejeon, Daejeon, Korea (the Republic of), (e-mail: ymro@kaist.ac.kr)","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.8446,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9169389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3654","last_page":"3667"},"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":0.9965000152587891,"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":0.9937999844551086,"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":0.7876783609390259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7333257794380188},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5199305415153503},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.4778580069541931},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.46820881962776184},{"id":"https://openalex.org/keywords/echoic-memory","display_name":"Echoic memory","score":0.4440818428993225},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41499772667884827},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.32273587584495544},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.1250559687614441},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1041797399520874},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.08374586701393127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876783609390259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7333257794380188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5199305415153503},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.4778580069541931},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.46820881962776184},{"id":"https://openalex.org/C11626679","wikidata":"https://www.wikidata.org/wiki/Q18651","display_name":"Echoic memory","level":3,"score":0.4440818428993225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41499772667884827},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32273587584495544},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.1250559687614441},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1041797399520874},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.08374586701393127},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3126925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3126925","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:koasas.kaist.ac.kr:10203/290797","is_oa":false,"landing_page_url":"http://hdl.handle.net/10203/290797","pdf_url":null,"source":{"id":"https://openalex.org/S4306402435","display_name":"KAIST Institutional Repository (KAIST)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157485424","host_organization_name":"Korea Advanced Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I157485424"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1965555277","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2067295501","https://openalex.org/W2120847449","https://openalex.org/W2121486117","https://openalex.org/W2131774270","https://openalex.org/W2134867751","https://openalex.org/W2194775991","https://openalex.org/W2290028669","https://openalex.org/W2516001803","https://openalex.org/W2551572271","https://openalex.org/W2585824449","https://openalex.org/W2594690981","https://openalex.org/W2625027024","https://openalex.org/W2749651610","https://openalex.org/W2766812927","https://openalex.org/W2808706139","https://openalex.org/W2887437849","https://openalex.org/W2888868298","https://openalex.org/W2890952074","https://openalex.org/W2897353073","https://openalex.org/W2898035430","https://openalex.org/W2910267084","https://openalex.org/W2947883281","https://openalex.org/W2951008357","https://openalex.org/W2953044442","https://openalex.org/W2963019222","https://openalex.org/W2963307811","https://openalex.org/W2963448850","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963680240","https://openalex.org/W2964171275","https://openalex.org/W2964199361","https://openalex.org/W2964243274","https://openalex.org/W2964352155","https://openalex.org/W2964404767","https://openalex.org/W2965390715","https://openalex.org/W2966792645","https://openalex.org/W2970006822","https://openalex.org/W2970270554","https://openalex.org/W2972563022","https://openalex.org/W2973068670","https://openalex.org/W2987172297","https://openalex.org/W2996414377","https://openalex.org/W3016011581","https://openalex.org/W3033703941","https://openalex.org/W3035042697","https://openalex.org/W3035626590","https://openalex.org/W3093712593","https://openalex.org/W3096650361","https://openalex.org/W3098686642","https://openalex.org/W3099078140","https://openalex.org/W3101481642","https://openalex.org/W3101689408","https://openalex.org/W3115683960","https://openalex.org/W3127334095","https://openalex.org/W3127645834","https://openalex.org/W3160305627","https://openalex.org/W4294619240","https://openalex.org/W4298112588","https://openalex.org/W4298642009","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638318767","https://openalex.org/W6638667902","https://openalex.org/W6696494075","https://openalex.org/W6732703391","https://openalex.org/W6732872814","https://openalex.org/W6743555153","https://openalex.org/W6745697700","https://openalex.org/W6752888775","https://openalex.org/W6763296340","https://openalex.org/W6767111847","https://openalex.org/W6767349417","https://openalex.org/W6787577988","https://openalex.org/W6843673214","https://openalex.org/W6844105982"],"related_works":["https://openalex.org/W3012016980","https://openalex.org/W2329452785","https://openalex.org/W2356380379","https://openalex.org/W2363925233","https://openalex.org/W2365159439","https://openalex.org/W2366284060","https://openalex.org/W1794016765","https://openalex.org/W2391464953","https://openalex.org/W2016354305","https://openalex.org/W3097230956"],"abstract_inverted_index":{"The":[0,54],"goal":[1],"of":[2,118,141,181,230,247],"this":[3],"work":[4],"is":[5],"to":[6,28,38,43,63,126,263],"reconstruct":[7,264],"speech":[8,46,137,191],"from":[9,47,192],"silent":[10,193],"video,":[11,194],"in":[12,114,163],"both":[13,147,237],"speaker":[14,17,30,200,240],"dependent":[15,31],"and":[16,50,68,90,104,149,195,199,207,219,222,239,243],"independent":[18,201,241],"ways.":[19],"Unlike":[20],"previous":[21,231],"works":[22],"that":[23,61,73,177,183,224,255],"have":[24],"been":[25],"mostly":[26],"restricted":[27],"a":[29],"setting,":[32],"we":[33,234],"propose":[34],"Visual":[35,85,174,249,257],"Voice":[36,86,175,250,258],"memory":[37,56,87,92,96,106,125,176,259],"restore":[39],"essential":[40],"auditory":[41,59,71,161,205],"information":[42,60,140,151,180,262],"generate":[44],"proper":[45],"different":[48],"speakers":[49],"even":[51],"unseen":[52],"speakers.":[53],"proposed":[55,215],"takes":[57],"additional":[58,160],"corresponds":[62],"the":[64,70,78,84,101,111,115,119,131,136,164,173,185,208,214,228,245,248,256],"input":[65,80,162],"face":[66],"movements":[67],"stores":[69],"contexts":[72],"can":[74,133],"be":[75],"recalled":[76],"by":[77,203],"given":[79],"visual":[81,112,186,210],"features.":[82,122,211],"Specifically,":[83],"contains":[88,260],"value":[89,95],"key":[91,105,168],"slots,":[93],"where":[94],"slots":[97,107],"are":[98,108],"for":[99,109],"saving":[100],"audio":[102,121,150,182],"features,":[103,187],"storing":[110],"features":[113,206],"same":[116],"location":[117],"saved":[120],"Guiding":[123],"each":[124,129],"properly":[127],"save":[128],"feature,":[130],"model":[132],"adequately":[134],"produce":[135],"through":[138],"auxiliary":[139],"audio.":[142],"Hence,":[143],"our":[144,225],"method":[145,226],"employs":[146],"video":[148],"during":[152],"training":[153,202],"time,":[154],"but":[155],"does":[156],"not":[157],"require":[158],"any":[159],"inference":[165],"time.":[166],"Our":[167],"contributions":[169],"are:":[170],"(1)":[171],"proposing":[172],"brings":[178],"rich":[179],"complements":[184],"thus":[188],"producing":[189],"high-quality":[190],"(2)":[196],"enabling":[197],"multi-speaker":[198,238],"memorizing":[204],"corresponding":[209],"We":[212,252],"validate":[213],"framework":[216],"on":[217,236],"GRID":[218],"Lip2Wav":[220],"datasets":[221],"show":[223],"surpasses":[227],"performance":[229],"works.":[232],"Moreover,":[233],"experiment":[235],"settings":[242],"verify":[244],"effectiveness":[246],"memory.":[251],"also":[253],"demonstrate":[254],"meaningful":[261],"speech.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}