{"id":"https://openalex.org/W4375868826","doi":"https://doi.org/10.1109/icassp49357.2023.10097209","title":"MODEFORMER: Modality-Preserving Embedding For Audio-Video Synchronization Using Transformers","display_name":"MODEFORMER: Modality-Preserving Embedding For Audio-Video Synchronization Using Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868826","doi":"https://doi.org/10.1109/icassp49357.2023.10097209"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097209","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":"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/A5100643250","display_name":"Akash Gupta","orcid":"https://orcid.org/0000-0001-7305-055X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Akash Gupta","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108711709","display_name":"Rohun Tripathi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohun Tripathi","raw_affiliation_strings":["Amazon Studios"],"affiliations":[{"raw_affiliation_string":"Amazon Studios","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061226360","display_name":"Wondong Jang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wondong Jang","raw_affiliation_strings":["Amazon Studios"],"affiliations":[{"raw_affiliation_string":"Amazon Studios","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100643250"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":1.0189,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74923318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9991999864578247,"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":0.8134505152702332},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5608025789260864},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.519199013710022},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5132396221160889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5106645226478577},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.45985135436058044},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4377889931201935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4371935725212097},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42873528599739075},{"id":"https://openalex.org/keywords/lagging","display_name":"Lagging","score":0.4167087972164154},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4141693115234375},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3800814747810364},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33284640312194824},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3054698705673218},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10284006595611572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0710228681564331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134505152702332},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5608025789260864},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.519199013710022},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5132396221160889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5106645226478577},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.45985135436058044},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4377889931201935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4371935725212097},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42873528599739075},{"id":"https://openalex.org/C2776962539","wikidata":"https://www.wikidata.org/wiki/Q6472078","display_name":"Lagging","level":2,"score":0.4167087972164154},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4141693115234375},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3800814747810364},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33284640312194824},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3054698705673218},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10284006595611572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0710228681564331},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097209","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":21,"referenced_works":["https://openalex.org/W2082942761","https://openalex.org/W2100561338","https://openalex.org/W2122591539","https://openalex.org/W2164899449","https://openalex.org/W2194775991","https://openalex.org/W2604379605","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2950864153","https://openalex.org/W2963654155","https://openalex.org/W3015830103","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W4297841713","https://openalex.org/W4385245566","https://openalex.org/W6675048546","https://openalex.org/W6684193366","https://openalex.org/W6739901393","https://openalex.org/W6754420807","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W1546240199","https://openalex.org/W2109142991","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Lack":[0],"of":[1,64,93,98,109],"audio-video":[2],"synchronization":[3],"is":[4,24,37],"a":[5,73,88,102],"common":[6],"problem":[7],"during":[8],"television":[9],"broadcasts":[10],"and":[11,48,96,123],"video":[12,49],"conferencing,":[13],"leading":[14,38],"to":[15,25,71,104],"an":[16,27],"unsatisfactory":[17],"viewing":[18],"experience.":[19],"A":[20],"widely":[21],"accepted":[22],"paradigm":[23],"create":[26],"error":[28],"detection":[29,137],"mechanism":[30],"that":[31,115],"identifies":[32],"the":[33,56,62,65,91,107],"cases":[34],"when":[35],"audio":[36,47,80],"or":[39],"lagging.":[40],"We":[41],"propose":[42,87],"ModEFormer,":[43],"which":[44,68],"independently":[45],"extracts":[46],"embeddings":[50],"using":[51],"modality-specific":[52],"transformers.":[53],"Different":[54],"from":[55],"other":[57],"transformer-based":[58],"approaches,":[59],"ModEFormer":[60,116,131],"preserves":[61],"modality":[63],"input":[66],"streams":[67],"allows":[69],"us":[70],"use":[72],"larger":[74],"batch":[75,103],"size":[76],"with":[77],"more":[78],"negative":[79,94],"samples":[81,95,100],"for":[82,121,125,135,138],"contrastive":[83],"learning.":[84],"Further,":[85],"we":[86,128],"tradeoff":[89],"between":[90],"number":[92,97],"unique":[99],"in":[101],"significantly":[105],"exceed":[106],"performance":[108],"previous":[110],"methods.":[111],"Experimental":[112],"results":[113],"show":[114],"achieves":[117],"state-of-the-art":[118],"performance,":[119],"94.5%":[120],"LRS2":[122],"90.9%":[124],"LRS3.":[126],"Finally,":[127],"demonstrate":[129],"how":[130],"can":[132],"be":[133],"used":[134],"offset":[136],"test":[139],"clips.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}