{"id":"https://openalex.org/W4390691978","doi":"https://doi.org/10.1109/tmm.2024.3352388","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","display_name":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390691978","doi":"https://doi.org/10.1109/tmm.2024.3352388"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3352388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3352388","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/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":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0002-8135-6625","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, 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":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6514-0018","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725649","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0009-0005-6817-604X"},"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":"Jeongsoo Choi","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0005-6817-604X","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055987476","display_name":"Dae Hoe Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dae Hoe Kim","raw_affiliation_strings":["Visual Intelligence Research Section, Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6628-3010","affiliations":[{"raw_affiliation_string":"Visual Intelligence Research Section, Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"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":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2232,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.94756948,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"6462","last_page":"6474"},"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":0.972100019454956,"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":0.967199981212616,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8577238917350769},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.7582334280014038},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7179544568061829},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7068933844566345},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5229204893112183},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5103797316551208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4694368839263916},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.44688668847084045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37625712156295776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3272010087966919},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3117603063583374},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2399371862411499},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12801611423492432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577238917350769},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.7582334280014038},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7179544568061829},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7068933844566345},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5229204893112183},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5103797316551208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4694368839263916},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.44688668847084045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37625712156295776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3272010087966919},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3117603063583374},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2399371862411499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12801611423492432},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3352388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3352388","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5178579001","display_name":null,"funder_award_id":"NRF-2022R1A2C2005529","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":104,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1821462560","https://openalex.org/W1983364832","https://openalex.org/W2090479364","https://openalex.org/W2115252128","https://openalex.org/W2121486117","https://openalex.org/W2127141656","https://openalex.org/W2132999255","https://openalex.org/W2134867751","https://openalex.org/W2171180249","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2604769302","https://openalex.org/W2752796333","https://openalex.org/W2766219058","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2947883281","https://openalex.org/W2963526065","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963979492","https://openalex.org/W2964051877","https://openalex.org/W2964199361","https://openalex.org/W2964216321","https://openalex.org/W2964352155","https://openalex.org/W2965390715","https://openalex.org/W2968124245","https://openalex.org/W2972756321","https://openalex.org/W2981501041","https://openalex.org/W2981851019","https://openalex.org/W2996970093","https://openalex.org/W2997591391","https://openalex.org/W2997918867","https://openalex.org/W3006974783","https://openalex.org/W3007589762","https://openalex.org/W3015830103","https://openalex.org/W3016011581","https://openalex.org/W3033703941","https://openalex.org/W3035042697","https://openalex.org/W3049478012","https://openalex.org/W3090449556","https://openalex.org/W3099839483","https://openalex.org/W3127334095","https://openalex.org/W3127645834","https://openalex.org/W3128564814","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3180355996","https://openalex.org/W3180374548","https://openalex.org/W3181942264","https://openalex.org/W3188015800","https://openalex.org/W3192404838","https://openalex.org/W3197567540","https://openalex.org/W3200601846","https://openalex.org/W3203789665","https://openalex.org/W3205193540","https://openalex.org/W3209059054","https://openalex.org/W3211224152","https://openalex.org/W4224319127","https://openalex.org/W4225305629","https://openalex.org/W4236398794","https://openalex.org/W4285144981","https://openalex.org/W4285436703","https://openalex.org/W4297808394","https://openalex.org/W4297841411","https://openalex.org/W4297841719","https://openalex.org/W4298112588","https://openalex.org/W4307286264","https://openalex.org/W4312444556","https://openalex.org/W4312638101","https://openalex.org/W4312784228","https://openalex.org/W4312920990","https://openalex.org/W4312975593","https://openalex.org/W4372259972","https://openalex.org/W4372260478","https://openalex.org/W4375869259","https://openalex.org/W4385245566","https://openalex.org/W4385488912","https://openalex.org/W4385822683","https://openalex.org/W4386076364","https://openalex.org/W4394671563","https://openalex.org/W6638523607","https://openalex.org/W6677618333","https://openalex.org/W6732742072","https://openalex.org/W6732872814","https://openalex.org/W6751751081","https://openalex.org/W6754420807","https://openalex.org/W6755207826","https://openalex.org/W6763296340","https://openalex.org/W6767279747","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6790356757","https://openalex.org/W6791353385","https://openalex.org/W6800067673","https://openalex.org/W6803378298","https://openalex.org/W6810168380","https://openalex.org/W6840070059","https://openalex.org/W6844194202","https://openalex.org/W6847652939"],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W2069501481","https://openalex.org/W2157598242","https://openalex.org/W2063862874","https://openalex.org/W46679383","https://openalex.org/W1911859126","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Visual":[0,39],"Speech":[1,40],"Recognition":[2,41],"(VSR)":[3],"is":[4,16,131],"the":[5,24,46,59,62,79,91,95,108,113,127,135,138,150],"task":[6,21],"of":[7,23,50,82,137],"predicting":[8],"spoken":[9],"words":[10],"from":[11,58,94,112],"silent":[12],"lip":[13,28],"movements.":[14,29],"VSR":[15],"regarded":[17],"as":[18],"a":[19,72],"challenging":[20],"because":[22],"insufficient":[25,47],"information":[26,49,81,93],"on":[27,149],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"an":[35],"Audio":[36,102],"Knowledge":[37],"empowered":[38],"framework":[42],"(AKVSR)":[43],"to":[44],"complement":[45],"speech":[48],"visual":[51],"modality":[52],"by":[53,71,89],"using":[54],"audio":[55,68,75,83,87,96,110,115,123,129],"modality.":[56],"Different":[57],"previous":[60],"methods,":[61],"proposed":[63,139],"AKVSR":[64],"1)":[65],"utilizes":[66],"rich":[67],"knowledge":[69,84],"encoded":[70],"large-scale":[73],"pretrained":[74],"model,":[76],"2)":[77],"saves":[78],"linguistic":[80],"in":[85],"compact":[86,114,128],"memory":[88,130],"discarding":[90],"non-linguistic":[92],"through":[97,141],"quantization,":[98],"and":[99,144],"3)":[100],"includes":[101],"Bridging":[103],"Module":[104],"which":[105,117],"can":[106],"find":[107],"best-matched":[109],"features":[111],"memory,":[116],"makes":[118],"our":[119],"training":[120],"possible":[121],"without":[122],"inputs,":[124],"once":[125],"after":[126],"composed.":[132],"We":[133],"validate":[134],"effectiveness":[136],"method":[140],"extensive":[142],"experiments,":[143],"achieve":[145],"new":[146],"state-of-the-art":[147],"performances":[148],"widely-used":[151],"LRS3":[152],"dataset.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}