{"id":"https://openalex.org/W4372260478","doi":"https://doi.org/10.1109/icassp49357.2023.10094693","title":"Multi-Temporal Lip-Audio Memory for Visual Speech Recognition","display_name":"Multi-Temporal Lip-Audio Memory for Visual Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260478","doi":"https://doi.org/10.1109/icassp49357.2023.10094693"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089479205","display_name":"Jeong Hun Yeo","orcid":"https://orcid.org/0009-0002-8135-6625"},"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":"Jeong Hun Yeo","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","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":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","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":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","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":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.829133152961731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.733559787273407},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.7191687226295471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49476855993270874},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4901021420955658},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4651402533054352},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.45434778928756714},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4228765368461609},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41544950008392334},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33921873569488525},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.27323243021965027},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10335302352905273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829133152961731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.733559787273407},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.7191687226295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49476855993270874},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4901021420955658},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4651402533054352},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.45434778928756714},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4228765368461609},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41544950008392334},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33921873569488525},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.27323243021965027},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10335302352905273},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2090479364","https://openalex.org/W2550143307","https://openalex.org/W2897492880","https://openalex.org/W2947883281","https://openalex.org/W2970270554","https://openalex.org/W2996970093","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3119418740","https://openalex.org/W3127334095","https://openalex.org/W3127645834","https://openalex.org/W3128564814","https://openalex.org/W3128750130","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3197567540","https://openalex.org/W3205193540","https://openalex.org/W4224319127","https://openalex.org/W4224931249","https://openalex.org/W4225299282","https://openalex.org/W4308222710","https://openalex.org/W4312638101","https://openalex.org/W4312975593","https://openalex.org/W6734491695","https://openalex.org/W6755759972","https://openalex.org/W6784282757","https://openalex.org/W6802479302"],"related_works":["https://openalex.org/W2095307689","https://openalex.org/W2150288981","https://openalex.org/W2572763611","https://openalex.org/W131634123","https://openalex.org/W2109087058","https://openalex.org/W2152415671","https://openalex.org/W2106937330","https://openalex.org/W2497106782","https://openalex.org/W2539140714","https://openalex.org/W1593153379"],"abstract_inverted_index":{"Visual":[0],"Speech":[1,46],"Recognition":[2,47],"(VSR)":[3],"is":[4,78],"a":[5,9,55,101],"task":[6],"to":[7,26,68,104,124,137],"predict":[8],"sentence":[10],"or":[11],"word":[12],"from":[13,91,110],"lip":[14,73],"movements.":[15,74],"Some":[16],"works":[17],"have":[18],"been":[19],"recently":[20],"presented":[21],"which":[22],"use":[23,64],"audio":[24,66,88,95,108,121,127,143,148],"signals":[25,67],"supplement":[27],"visual":[28,111,152],"information.":[29],"However,":[30],"existing":[31],"methods":[32],"utilize":[33],"only":[34],"limited":[35],"information":[36,71],"such":[37],"as":[38],"phoneme-level":[39],"features":[40,89,109,112,128,149],"and":[41,93,97],"soft":[42],"labels":[43],"of":[44,65,72,81,132,161],"Automatic":[45],"(ASR)":[48],"networks.":[49],"In":[50,135],"this":[51],"paper,":[52],"we":[53,157],"present":[54],"Multi-Temporal":[56],"Lip-Audio":[57],"Memory":[58],"(MTLAM)":[59],"that":[60],"makes":[61],"the":[62,98,114,130,142,159,162],"best":[63],"complement":[69],"insufficient":[70],"The":[75],"proposed":[76],"method":[77],"mainly":[79],"composed":[80],"two":[82,168],"parts:":[83],"1)":[84],"MT-LAM":[85],"saves":[86],"multi-temporal":[87,107,126],"produced":[90],"short-":[92],"long-term":[94],"signals,":[96],"MTLAM":[99,163],"memorizes":[100],"visual-to-audio":[102,140],"mapping":[103],"load":[105],"stored":[106],"at":[113],"inference":[115],"phase.":[116],"2)":[117],"We":[118],"design":[119],"an":[120],"temporal":[122,144],"model":[123],"produce":[125],"capturing":[129],"context":[131],"neighboring":[133],"words.":[134],"addition,":[136],"construct":[138],"effective":[139],"mapping,":[141],"models":[145],"can":[146],"generate":[147],"time-aligned":[150],"with":[151],"features.":[153],"Through":[154],"extensive":[155],"experiments,":[156],"validate":[158],"effectiveness":[160],"achieving":[164],"state-of-the-art":[165],"performances":[166],"on":[167],"public":[169],"VSR":[170],"datasets.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}