{"id":"https://openalex.org/W4392909516","doi":"https://doi.org/10.1109/icassp48485.2024.10446372","title":"Multimodal Transformer Distillation for Audio-Visual Synchronization","display_name":"Multimodal Transformer Distillation for Audio-Visual Synchronization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909516","doi":"https://doi.org/10.1109/icassp48485.2024.10446372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5083897242","display_name":"Xuanjun Chen","orcid":"https://orcid.org/0009-0002-5930-3797"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xuanjun Chen","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering","Graduate Institute of Communication Engineering, National Taiwan University","Department of Computer Science and Information Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering","Graduate Institute of Communication Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054435952","display_name":"Chung-Che Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Che Wang","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering","Department of Computer Science and Information Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering","Department of Computer Science and Information Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering","Department of Computer Science and Information Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":14.3917,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98668665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7755","last_page":"7759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.8312000036239624,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.8312000036239624,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7649000287055969,"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":0.7287769317626953},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7056158781051636},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5887826681137085},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5693588852882385},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5322202444076538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36948683857917786},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.25462210178375244},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1423511803150177},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11438798904418945},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08639922738075256},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0600627064704895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287769317626953},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7056158781051636},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5887826681137085},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5693588852882385},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5322202444076538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36948683857917786},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25462210178375244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1423511803150177},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11438798904418945},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08639922738075256},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0600627064704895},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2517273615","https://openalex.org/W2561238782","https://openalex.org/W2731516819","https://openalex.org/W2739879705","https://openalex.org/W2804823968","https://openalex.org/W2887783173","https://openalex.org/W2890952074","https://openalex.org/W2936864631","https://openalex.org/W2950864153","https://openalex.org/W2962960500","https://openalex.org/W2963140444","https://openalex.org/W2963534679","https://openalex.org/W2964111476","https://openalex.org/W2982242214","https://openalex.org/W2986015886","https://openalex.org/W3008374555","https://openalex.org/W3016663370","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3116298410","https://openalex.org/W3154852953","https://openalex.org/W3176403475","https://openalex.org/W3206008172","https://openalex.org/W4214698081","https://openalex.org/W4297841713","https://openalex.org/W4306867196","https://openalex.org/W4308663722","https://openalex.org/W4319862411","https://openalex.org/W4385245566","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6730179637","https://openalex.org/W6735927292","https://openalex.org/W6740493225","https://openalex.org/W6748082341","https://openalex.org/W6752178629","https://openalex.org/W6769906912","https://openalex.org/W6773815586","https://openalex.org/W6810980340"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Audio-visual":[0],"synchronization":[1],"aims":[2],"to":[3,24,63,81],"determine":[4],"whether":[5],"the":[6,12,66,72,84,99,111,134],"mouth":[7],"movements":[8],"and":[9,69,123,129],"speech":[10],"in":[11,71,95],"video":[13],"are":[14],"synchronized.":[15],"VocaLiST":[16,138],"reaches":[17],"state-of-the-art":[18],"performance":[19,114],"by":[20,50,127,139],"incorporating":[21],"multimodal":[22,53],"Transformers":[23],"model":[25,62,135],"audio-visual":[26],"interact":[27],"information.":[28],"However,":[29],"it":[30,36],"requires":[31],"high":[32],"computing":[33],"resources,":[34],"making":[35],"impractical":[37],"for":[38],"real-world":[39],"applications.":[40],"This":[41],"paper":[42],"proposed":[43,52,91],"an":[44],"MTD-VocaLiST":[45],"model,":[46],"which":[47],"is":[48,93],"trained":[49],"our":[51],"Transformer":[54,73],"distillation":[55,100,108],"(MTD)":[56],"loss.":[57],"MTD":[58,103],"loss":[59,104],"enables":[60],"MTDVocaLiST":[61,117,132],"deeply":[64],"mimic":[65],"cross-attention":[67],"distribution":[68],"value-relation":[70],"of":[74,137],"VocaLiST.":[75],"Additionally,":[76],"we":[77],"harness":[78],"uncertainty":[79],"weighting":[80],"fully":[82],"exploit":[83],"interaction":[85],"information":[86],"across":[87],"all":[88],"layers.":[89],"Our":[90],"method":[92,101],"effective":[94],"two":[96],"aspects:":[97],"From":[98,110],"perspective,":[102],"outperforms":[105,118],"other":[106],"strong":[107],"baselines.":[109],"distilled":[112],"model\u2019s":[113],"perspective:":[115],"1)":[116],"similar-size":[119],"SOTA":[120],"models,":[121],"SyncNet,":[122],"Perfect":[124],"Match":[125],"models":[126],"15.65%":[128],"3.35%;":[130],"2)":[131],"reduces":[133],"size":[136],"83.52%,":[140],"yet":[141],"still":[142],"maintaining":[143],"similar":[144],"performance.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}