{"id":"https://openalex.org/W4408352877","doi":"https://doi.org/10.1109/icassp49660.2025.10888166","title":"Advancing Active Speaker Detection for Egocentric Videos","display_name":"Advancing Active Speaker Detection for Egocentric Videos","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352877","doi":"https://doi.org/10.1109/icassp49660.2025.10888166"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888166","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/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025328200","display_name":"Juan Ortiz Sanz","orcid":"https://orcid.org/0000-0003-0717-0400"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Azcarreta Ortiz","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058219648","display_name":"Ali Aroudi","orcid":"https://orcid.org/0000-0001-5770-0858"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Aroudi","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102789202","display_name":"Daniel D.E. Wong","orcid":"https://orcid.org/0000-0002-7781-1149"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel D.E. Wong","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056969511","display_name":"Francesco Nesta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francesco Nesta","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055065049","display_name":"Jacob Donley","orcid":"https://orcid.org/0000-0002-8401-798X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Donley","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.128,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85146264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9979000091552734,"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":0.9979000091552734,"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":0.9391000270843506,"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":0.9258999824523926,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7273927927017212},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43818148970603943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42193394899368286},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40956899523735046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273927927017212},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43818148970603943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42193394899368286},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40956899523735046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888166","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":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2307770531","https://openalex.org/W2604379605","https://openalex.org/W2609107023","https://openalex.org/W2738579427","https://openalex.org/W2776004874","https://openalex.org/W2798840374","https://openalex.org/W2808631503","https://openalex.org/W2949662773","https://openalex.org/W2950864153","https://openalex.org/W2963173190","https://openalex.org/W2963312584","https://openalex.org/W2963371159","https://openalex.org/W3016098309","https://openalex.org/W3024869864","https://openalex.org/W3034702511","https://openalex.org/W3038871978","https://openalex.org/W3087144913","https://openalex.org/W3095435396","https://openalex.org/W3170697543","https://openalex.org/W3176165731","https://openalex.org/W3205786327","https://openalex.org/W3206008172","https://openalex.org/W4225672218","https://openalex.org/W4286378963","https://openalex.org/W4312356258","https://openalex.org/W4312466984","https://openalex.org/W4385822356","https://openalex.org/W4386075942","https://openalex.org/W4386076005","https://openalex.org/W4386083051","https://openalex.org/W4400433339","https://openalex.org/W4402716327","https://openalex.org/W4402754289","https://openalex.org/W6763136721","https://openalex.org/W6797761920","https://openalex.org/W6810459795","https://openalex.org/W6846145006"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"improved":[4],"approach":[5],"to":[6,16,36,147],"multimodal":[7],"active":[8],"speaker":[9,149],"detection":[10],"in":[11,28,47,64,139],"egocentric":[12,70],"videos,":[13],"specifically":[14],"designed":[15],"be":[17],"robust":[18],"against":[19],"the":[20,38,44,48,61,66,74,96,100,118,126,130,140],"rapid":[21],"movements":[22],"and":[23,51,129],"motion":[24,54,123],"blur":[25,55,124],"commonly":[26],"found":[27],"such":[29],"videos.":[30,71],"We":[31,72],"propose":[32],"two":[33],"key":[34],"techniques":[35,78],"improve":[37],"model\u2019s":[39,62],"resilience:":[40],"(i)":[41],"spatially":[42],"fixing":[43],"lip":[45],"region":[46],"visual":[49,121],"input,":[50,122],"(ii)":[52],"applying":[53],"augmentation.":[56],"These":[57],"methods":[58],"significantly":[59],"enhance":[60],"performance":[63,94],"handling":[65],"challenges":[67],"typical":[68],"of":[69,76,120,132],"showcase":[73],"effectiveness":[75],"these":[77],"on":[79,95,154],"a":[80,110],"simple":[81],"but":[82],"efficient":[83],"causal":[84],"audio-visual":[85,148],"model.":[86],"The":[87],"proposed":[88],"model,":[89],"named":[90],"EgoASD,":[91],"demonstrates":[92],"state-of-the-art":[93],"EasyCom":[97],"dataset,":[98],"beating":[99],"previous":[101],"SOTA":[102],"by":[103],"1.7%":[104],"mean":[105],"Average":[106],"Precision":[107],"(mAP)":[108],"with":[109],"model":[111,146],"2.5":[112],"times":[113],"smaller.":[114],"Our":[115],"ablations":[116],"highlight":[117],"importance":[119,131],"augmentation,":[125],"pretraining":[127],"method":[128],"temporal":[133],"context.":[134],"To":[135],"demonstrate":[136],"its":[137],"applicability":[138],"real":[141],"world,":[142],"we":[143],"apply":[144],"our":[145],"diarization,":[150],"outperforming":[151],"other":[152],"baselines":[153],"EasyCom.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
