{"id":"https://openalex.org/W4392908938","doi":"https://doi.org/10.1109/icassp48485.2024.10448124","title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","display_name":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908938","doi":"https://doi.org/10.1109/icassp48485.2024.10448124"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448124","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/A5062754007","display_name":"Chaeyoung Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chaeyoung Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649773","display_name":"Suyeon Lee","orcid":"https://orcid.org/0000-0002-1468-3768"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suyeon Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102335705","display_name":"Ki-Hyun Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kihyun Nam","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003708446","display_name":"Kyeongha Rho","orcid":"https://orcid.org/0009-0001-6487-5418"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyeongha Rho","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022133103","display_name":"You Jin Kim","orcid":"https://orcid.org/0000-0002-4952-5532"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"You Jin Kim","raw_affiliation_strings":["Naver Cloud Corporation,South Korea","Naver Cloud Corporation, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013499323","display_name":"Youngjoon Jang","orcid":"https://orcid.org/0009-0002-0500-6025"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Jang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062754007"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":3.8676,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94144192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8391","last_page":"8395"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8343831300735474},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7653370499610901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5950617790222168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5180099606513977},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4682639241218567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3730156123638153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33194974064826965},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07060378789901733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343831300735474},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7653370499610901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5950617790222168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180099606513977},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4682639241218567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3730156123638153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33194974064826965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07060378789901733},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448124","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":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2604379605","https://openalex.org/W2890952074","https://openalex.org/W2962960500","https://openalex.org/W2964171275","https://openalex.org/W2972729214","https://openalex.org/W3016098309","https://openalex.org/W3016663370","https://openalex.org/W3034702511","https://openalex.org/W3038871978","https://openalex.org/W3172472082","https://openalex.org/W3197584784","https://openalex.org/W4214701094","https://openalex.org/W4312268709","https://openalex.org/W4312466984","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W4402754289","https://openalex.org/W6631190155","https://openalex.org/W6798523648","https://openalex.org/W6849258529"],"related_works":["https://openalex.org/W1564680838","https://openalex.org/W2060591604","https://openalex.org/W1505626156","https://openalex.org/W2166791242","https://openalex.org/W3012440055","https://openalex.org/W2585162246","https://openalex.org/W2034202275","https://openalex.org/W1934413089","https://openalex.org/W1992291644","https://openalex.org/W2098419343"],"abstract_inverted_index":{"The":[0,57,117],"goal":[1],"of":[2,24,64,89],"this":[3,47],"work":[4],"is":[5,17,59,74],"Active":[6],"Speaker":[7],"Detection":[8],"(ASD),":[9],"a":[10,15,22,52,69],"task":[11,33],"to":[12,62,81],"determine":[13],"whether":[14],"person":[16,70],"speaking":[18],"or":[19,114],"not":[20],"in":[21],"series":[23],"video":[25],"frames.":[26],"Previous":[27],"works":[28],"have":[29],"dealt":[30],"with":[31,100],"the":[32,65,72,79,86,101,109,128],"by":[34],"exploring":[35],"network":[36],"architectures":[37],"while":[38],"learning":[39],"effective":[40,83],"representations":[41,84],"has":[42],"been":[43],"less":[44],"explored.":[45],"In":[46],"work,":[48],"we":[49],"propose":[50],"TalkNCE,":[51],"novel":[53],"talk-aware":[54],"contrastive":[55],"loss.":[56],"loss":[58,95,122],"only":[60],"applied":[61],"part":[63],"full":[66],"segments":[67],"where":[68],"on":[71,140],"screen":[73],"actually":[75],"speaking.":[76],"This":[77],"encourages":[78],"model":[80],"learn":[82],"through":[85],"natural":[87],"correspondence":[88],"speech":[90],"and":[91,142],"facial":[92],"movements.":[93],"Our":[94,135],"can":[96,123],"be":[97,124],"jointly":[98],"optimized":[99],"existing":[102,129],"objectives":[103],"for":[104,111],"training":[105,115],"ASD":[106,130],"models":[107],"without":[108],"need":[110],"additional":[112],"supervision":[113],"data.":[116],"experiments":[118],"demonstrate":[119],"that":[120],"our":[121],"easily":[125],"integrated":[126],"into":[127],"frameworks,":[131],"improving":[132],"their":[133],"performance.":[134],"method":[136],"achieves":[137],"state-of-the-art":[138],"performances":[139],"AVA-ActiveSpeaker":[141],"ASW":[143],"datasets.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}