{"id":"https://openalex.org/W4408347324","doi":"https://doi.org/10.1109/icassp49660.2025.10888378","title":"Audio-Visual Representation Learning For Lip-Sync Estimation Through Ranking Augmented Contrastive Training","display_name":"Audio-Visual Representation Learning For Lip-Sync Estimation Through Ranking Augmented Contrastive Training","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347324","doi":"https://doi.org/10.1109/icassp49660.2025.10888378"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5025819525","display_name":"Bhavin Jawade","orcid":"https://orcid.org/0009-0008-6059-5364"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bhavin Jawade","raw_affiliation_strings":["Netflix Inc"],"affiliations":[{"raw_affiliation_string":"Netflix Inc","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050071432","display_name":"Ravi Teja Gadde","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Teja Gadde","raw_affiliation_strings":["Netflix Inc"],"affiliations":[{"raw_affiliation_string":"Netflix Inc","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116592024","display_name":"Christophe Bejjani","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christophe Bejjani","raw_affiliation_strings":["Netflix Inc"],"affiliations":[{"raw_affiliation_string":"Netflix Inc","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yinghong Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinghong Lan","raw_affiliation_strings":["Netflix Inc"],"affiliations":[{"raw_affiliation_string":"Netflix Inc","institution_ids":["https://openalex.org/I869089601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025819525"],"corresponding_institution_ids":["https://openalex.org/I869089601"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.039306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9994000196456909,"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":0.9994000196456909,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9358000159263611,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11448","display_name":"Face recognition and analysis","score":0.9075000286102295,"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":0.7989122867584229},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.7192420959472656},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6514854431152344},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5935589075088501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5872424244880676},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5451277494430542},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4865626394748688},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4771380126476288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47159087657928467},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.418972909450531},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3791424334049225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3351774215698242},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32971203327178955},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.09837564826011658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989122867584229},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.7192420959472656},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6514854431152344},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5935589075088501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872424244880676},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5451277494430542},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4865626394748688},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4771380126476288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47159087657928467},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.418972909450531},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3791424334049225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3351774215698242},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32971203327178955},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.09837564826011658},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2604379605","https://openalex.org/W2950864153","https://openalex.org/W2963019222","https://openalex.org/W2964271799","https://openalex.org/W3010457696","https://openalex.org/W3034202663","https://openalex.org/W3206008172","https://openalex.org/W4283819318","https://openalex.org/W4297841713","https://openalex.org/W4319299730","https://openalex.org/W4319299938","https://openalex.org/W4375868826","https://openalex.org/W4392909516","https://openalex.org/W6739901393","https://openalex.org/W6810980340","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4392306433","https://openalex.org/W2524993630","https://openalex.org/W2063547430","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W1878822803","https://openalex.org/W1995263003","https://openalex.org/W2222580448"],"abstract_inverted_index":{"In":[0],"many":[1],"applications,":[2],"particularly":[3],"in":[4,61,98,177],"media":[5],"production":[6],"and":[7,15,74,154],"content":[8],"localization,":[9],"it":[10,53],"is":[11,68],"crucial":[12],"to":[13,39,55,88,96,142,149,174],"detect":[14],"evaluate":[16],"varying":[17,91],"degrees":[18],"of":[19,93,106,163,171],"audio-visual":[20],"synchronization,":[21,58],"such":[22,59],"as":[23,60,133,167],"selecting":[24],"high-quality":[25],"dubbed":[26,62],"audio":[27,43,75],"over":[28],"poorly":[29],"synchronized":[30],"tracks.":[31],"Traditional":[32],"contrastively":[33],"pre-trained":[34],"LipSync":[35],"models":[36,49],"are":[37],"designed":[38],"distinguish":[40],"perfectly":[41],"synced":[42,72],"from":[44],"unsynced":[45,156],"audio.":[46],"However,":[47],"these":[48],"fall":[50],"short":[51],"when":[52],"comes":[54],"detecting":[56],"partial":[57],"audio,":[63],"because":[64],"their":[65,86],"training":[66],"objective":[67],"focused":[69],"on":[70],"pulling":[71],"lip-motion":[73],"closer":[76],"together":[77],"while":[78],"pushing":[79],"everything":[80],"else":[81],"apart.":[82],"This":[83],"approach":[84],"limits":[85],"ability":[87],"accurately":[89],"gauge":[90],"levels":[92],"sync,":[94],"leading":[95,173],"challenges":[97],"scenarios":[99],"that":[100],"require":[101],"a":[102,115,130,134,168],"more":[103],"nuanced":[104],"understanding":[105],"synchronization":[107],"quality.":[108],"To":[109],"address":[110],"this":[111,144],"limitation,":[112],"we":[113,159],"propose":[114],"novel":[116],"deep":[117],"metric":[118],"learning":[119],"approach,":[120],"the":[121,147,161],"Ranking":[122],"Supervised":[123],"Multi-Similarity":[124],"(RSMS)":[125],"loss":[126],"formulation,":[127],"which":[128],"introduces":[129],"ranking":[131],"prior":[132],"supervision":[135],"signal.":[136],"Our":[137],"method":[138],"integrates":[139],"hard-sample":[140],"mining":[141],"enforce":[143],"ranking,":[145],"allowing":[146],"model":[148],"better":[150],"differentiate":[151],"between":[152],"partial-syncs":[153],"completely":[155],"audios.":[157],"Furthermore,":[158],"demonstrate":[160],"effectiveness":[162],"using":[164],"\u201cDubbed":[165],"Audio\u201d":[166],"train-time":[169],"example":[170],"partial-syncs,":[172],"improved":[175],"performance":[176],"lip-sync":[178],"models.":[179]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}