{"id":"https://openalex.org/W4400527405","doi":"https://doi.org/10.1109/fg59268.2024.10581985","title":"Lip and Speech Synchronization using Supervised Contrastive Learning and Cross-Modal Attention","display_name":"Lip and Speech Synchronization using Supervised Contrastive Learning and Cross-Modal Attention","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400527405","doi":"https://doi.org/10.1109/fg59268.2024.10581985"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10581985","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fg59268.2024.10581985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5036559623","display_name":"Munender Varshney","orcid":"https://orcid.org/0000-0002-3061-5757"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Munender Varshney","raw_affiliation_strings":["R&D Centre, Hitachi India Pvt Ltd,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"R&D Centre, Hitachi India Pvt Ltd,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099842996","display_name":"Mayurakshi Mukherji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mayurakshi Mukherji","raw_affiliation_strings":["R&D Centre, Hitachi India Pvt Ltd,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"R&D Centre, Hitachi India Pvt Ltd,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080895330","display_name":"Senthil Raja G","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Senthil Raja G","raw_affiliation_strings":["R&D Centre, Hitachi India Pvt Ltd,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"R&D Centre, Hitachi India Pvt Ltd,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113206710","display_name":"Ananth Ganesh","orcid":"https://orcid.org/0009-0002-2877-4086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananth Ganesh","raw_affiliation_strings":["R&D Centre, Hitachi India Pvt Ltd,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"R&D Centre, Hitachi India Pvt Ltd,Bangalore,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020275535","display_name":"Kingshuk Banerjee","orcid":"https://orcid.org/0009-0005-6655-0288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kingshuk Banerjee","raw_affiliation_strings":["R&D Centre, Hitachi India Pvt Ltd,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"R&D Centre, Hitachi India Pvt Ltd,Bangalore,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036559623"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11200343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","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":0.998199999332428,"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":0.998199999332428,"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/T11448","display_name":"Face recognition and analysis","score":0.90829998254776,"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":0.7692903280258179},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6897971630096436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6579328179359436},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.581732451915741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4551827609539032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.388214111328125},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09749147295951843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692903280258179},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6897971630096436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6579328179359436},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.581732451915741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4551827609539032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.388214111328125},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09749147295951843},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/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/fg59268.2024.10581985","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fg59268.2024.10581985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W193279279","https://openalex.org/W1522301498","https://openalex.org/W2082942761","https://openalex.org/W2122591539","https://openalex.org/W2162813706","https://openalex.org/W2604379605","https://openalex.org/W2890052321","https://openalex.org/W2890952074","https://openalex.org/W2950864153","https://openalex.org/W2962960500","https://openalex.org/W3010079658","https://openalex.org/W3010094231","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3142098745","https://openalex.org/W3161610222","https://openalex.org/W3207924272","https://openalex.org/W4213019189","https://openalex.org/W4283818626","https://openalex.org/W4287812705","https://openalex.org/W4297841713","https://openalex.org/W4301606627","https://openalex.org/W4308663722","https://openalex.org/W4319300274","https://openalex.org/W4385245566","https://openalex.org/W4386133969","https://openalex.org/W4390872997","https://openalex.org/W4392909516","https://openalex.org/W6607895473","https://openalex.org/W6631190155","https://openalex.org/W6754048563","https://openalex.org/W6756871312","https://openalex.org/W6776700526","https://openalex.org/W6794169909","https://openalex.org/W6797674293","https://openalex.org/W6810980340","https://openalex.org/W6855474243"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2380573388","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2369636957","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2029465934","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"temporal":[1,23,76,125],"consistency":[2],"between":[3,25,78,112],"audio":[4,29,117],"and":[5,16,28,82,91,109,116,163,199],"video":[6,27],"is":[7,55],"of":[8,53,85,141,166,195,208],"utmost":[9],"concern":[10],"for":[11,33,137,151],"understanding":[12],"the":[13,17,26,43,75,83,102,113,120,139,149,161,211],"lip":[14,86],"movements":[15],"corresponding":[18],"speech":[19,81],"content.":[20],"Learning":[21],"this":[22,70],"relationship":[24],"can":[30,61],"be":[31,62],"used":[32,63],"classification,":[34],"detection,":[35],"or":[36,48],"generation":[37],"purposes.":[38],"So,":[39],"identifying":[40],"if":[41,96],"both":[42,97],"modalities":[44,143],"are":[45,73,98],"temporally":[46,152],"consistent":[47],"not":[49],"i.e.,":[50],"synchronization":[51,126,171],"detection":[52],"modalities,":[54],"a":[56,79,132,164,192,205],"very":[57],"crucial":[58],"problem":[59],"that":[60,184],"to":[64,94,118,169],"solve":[65],"various":[66],"downstream":[67],"tasks.":[68],"In":[69],"work,":[71],"we":[72],"learning":[74,130],"correlation/mapping":[77],"speaker's":[80],"sequence":[84,104],"movement":[87],"in":[88,173],"an":[89,106,174],"unconstrained":[90,175],"large":[92],"vocabulary":[93],"identify":[95],"synchronized.":[99],"We":[100,123,155],"model":[101,159],"frame":[103,114,206],"using":[105,127,180],"encoder":[107],"network":[108],"use":[110],"cross-attention":[111],"sequences":[115],"learn":[119,124],"embeddings":[121],"jointly.":[122],"supervised":[128],"contrastive":[129],"with":[131,144,210],"hard":[133],"negative":[134],"sampling":[135],"strategy":[136],"differentiating":[138],"embedding":[140],"two":[142],"different":[145],"alignments":[146],"while":[147],"improving":[148],"similarity":[150],"aligned":[153],"ones.":[154],"have":[156],"trained":[157],"our":[158,185],"on":[160,188,202],"LRS2":[162,203],"dataset":[165,190],"singing":[167],"voices":[168],"evaluate":[170],"tasks":[172],"natural":[176],"setting.":[177],"Extensive":[178],"evaluation":[179],"qualitative":[181],"metrics":[182],"shows":[183],"method":[186],"outperforms":[187],"Acappella":[189],"by":[191],"good":[193],"margin":[194],"more":[196],"than":[197],"1.5%":[198],"0.5":[200],"%":[201],"across":[204],"count":[207],"5":[209],"state-of-the-art":[212],"model.":[213]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}