{"id":"https://openalex.org/W3206248339","doi":"https://doi.org/10.1145/3474085.3475420","title":"CALLip: Lipreading using Contrastive and Attribute Learning","display_name":"CALLip: Lipreading using Contrastive and Attribute Learning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206248339","doi":"https://doi.org/10.1145/3474085.3475420","mag":"3206248339"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5101492567","display_name":"Yiyang Huang","orcid":"https://orcid.org/0000-0002-1741-6649"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyang Huang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083213551","display_name":"Xuefeng Liang","orcid":"https://orcid.org/0000-0002-1448-0477"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Liang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003019748","display_name":"Chaowei Fang","orcid":"https://orcid.org/0000-0001-8805-9792"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaowei Fang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101492567"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.7716,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.7175455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2492","last_page":"2500"},"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":0.9955999851226807,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9681000113487244,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.7565978765487671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548142671585083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7137547731399536},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5363885760307312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4686813950538635},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4672410786151886},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.4433266818523407},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.43927234411239624},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4145946800708771},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4132833480834961},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3725094497203827},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25992029905319214},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1438165307044983},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.12877902388572693},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11365804076194763}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.7565978765487671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548142671585083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7137547731399536},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5363885760307312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4686813950538635},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4672410786151886},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.4433266818523407},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.43927234411239624},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4145946800708771},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4132833480834961},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3725094497203827},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25992029905319214},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1438165307044983},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.12877902388572693},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11365804076194763},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.550000011920929,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1915742967","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2026077962","https://openalex.org/W2115252128","https://openalex.org/W2168744723","https://openalex.org/W2171246813","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2551572271","https://openalex.org/W2555897561","https://openalex.org/W2587150483","https://openalex.org/W2604379605","https://openalex.org/W2626778328","https://openalex.org/W2741151796","https://openalex.org/W2785523195","https://openalex.org/W2798991696","https://openalex.org/W2802223794","https://openalex.org/W2842511635","https://openalex.org/W2905115762","https://openalex.org/W2948012107","https://openalex.org/W2952746495","https://openalex.org/W2963030892","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2964121744","https://openalex.org/W2964261768","https://openalex.org/W2970971581","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3005680577","https://openalex.org/W3035042697","https://openalex.org/W3035524453","https://openalex.org/W3035626590","https://openalex.org/W3086926995","https://openalex.org/W3103801904","https://openalex.org/W3108655343"],"related_works":["https://openalex.org/W1889843584","https://openalex.org/W2778699561","https://openalex.org/W2062208920","https://openalex.org/W3112945917","https://openalex.org/W4282592218","https://openalex.org/W2082487666","https://openalex.org/W2347215599","https://openalex.org/W2547288128","https://openalex.org/W171560785","https://openalex.org/W2591964346"],"abstract_inverted_index":{"Lipreading,":[0],"aiming":[1],"at":[2],"interpreting":[3],"speech":[4,20],"by":[5],"watching":[6],"the":[7,11,35,46,50,85,99,117,129,136],"lip":[8,37,52,100,150],"movements":[9,53],"of":[10,54,131,149],"speaker,":[12],"has":[13],"great":[14],"significance":[15],"in":[16],"human":[17],"communication":[18],"and":[19,78,124,134,157,162],"understanding.":[21],"Despite":[22],"having":[23],"reached":[24],"a":[25,69,90],"feasible":[26],"performance,":[27],"lipreading":[28,71,170],"still":[29],"faces":[30],"two":[31,65],"crucial":[32],"challenges:":[33],"1)":[34],"considerable":[36],"movement":[38],"variations":[39],"cross":[40],"different":[41],"persons":[42],"when":[43,56],"they":[44,57],"utter":[45,58],"same":[47],"words;":[48],"2)":[49],"similar":[51],"people":[55],"some":[59],"confused":[60],"phonemes.":[61],"To":[62],"tackle":[63],"these":[64],"problems,":[66],"we":[67],"propose":[68],"novel":[70],"framework,":[72],"CALLip,":[73],"which":[74,94],"employs":[75],"attribute":[76,82],"learning":[77,83,119],"contrastive":[79,118],"learning.":[80],"The":[81,152],"extracts":[84],"speaker":[86,91],"identity-aware":[87],"features":[88,133,148],"through":[89],"recognition":[92],"branch,":[93],"are":[95,110],"able":[96],"to":[97,102,127],"normalize":[98],"shapes":[101],"eliminate":[103],"cross-speaker":[104],"variations.":[105],"Considering":[106],"that":[107,143,165],"audio":[108,125],"signals":[109,126],"intrinsically":[111],"more":[112],"distinguishable":[113],"than":[114],"visual":[115,123,132],"signals,":[116],"is":[120],"devised":[121],"between":[122],"enhance":[128],"discrimination":[130],"alleviate":[135],"viseme":[137],"confusion":[138],"problem.":[139],"Experimental":[140],"results":[141],"show":[142],"CALLip":[144,166],"does":[145],"learn":[146],"better":[147],"movements.":[151],"comparisons":[153],"on":[154],"both":[155],"English":[156],"Chinese":[158],"benchmark":[159],"datasets,":[160],"GRID":[161],"CMLR,":[163],"demonstrate":[164],"outperforms":[167],"six":[168],"state-of-the-art":[169],"methods":[171],"without":[172],"using":[173],"any":[174],"additional":[175],"data.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}