{"id":"https://openalex.org/W7140771249","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443698","title":"Robust Training of Low-Parameter Models for Active Speaker Detection from Digital Videos","display_name":"Robust Training of Low-Parameter Models for Active Speaker Detection from Digital Videos","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7140771249","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443698"},"language":null,"primary_location":{"id":"doi:10.1109/ieeeconf67917.2025.11443698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","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/A5114414699","display_name":"Sebastian Janampa","orcid":null},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Janampa","raw_affiliation_strings":["The University of New Mexico,Department of Electrical and Computer Engineering,Albuquerque,NM,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New Mexico,Department of Electrical and Computer Engineering,Albuquerque,NM,USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130674442","display_name":"Bonnie Morales Ugarte","orcid":null},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bonnie Morales Ugarte","raw_affiliation_strings":["The University of New Mexico,Department of Electrical and Computer Engineering,Albuquerque,NM,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New Mexico,Department of Electrical and Computer Engineering,Albuquerque,NM,USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079839426","display_name":"Constantinos S. Pattichis","orcid":"https://orcid.org/0000-0003-1271-8151"},"institutions":[{"id":"https://openalex.org/I34771391","display_name":"University of Cyprus","ror":"https://ror.org/02qjrjx09","country_code":"CY","type":"education","lineage":["https://openalex.org/I34771391"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Constantinos S. Pattichis","raw_affiliation_strings":["University of Cyprus,Department of Computer Science,Nicosia,Cyprus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cyprus,Department of Computer Science,Nicosia,Cyprus","institution_ids":["https://openalex.org/I34771391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130639938","display_name":"Marios S. Pattichis","orcid":null},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marios S. Pattichis","raw_affiliation_strings":["The University of New Mexico,Department of Electrical and Computer Engineering,Albuquerque,NM,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New Mexico,Department of Electrical and Computer Engineering,Albuquerque,NM,USA","institution_ids":["https://openalex.org/I169521973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83441165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5152999758720398,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5152999758720398,"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/T10860","display_name":"Speech and Audio Processing","score":0.2930999994277954,"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/T10057","display_name":"Face and Expression Recognition","score":0.030700000002980232,"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/training","display_name":"Training (meteorology)","score":0.6650000214576721},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.336899995803833},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.30379998683929443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2881999909877777},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.25040000677108765}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6650000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3930000066757202},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25040000677108765},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2485000044107437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf67917.2025.11443698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2330149154","https://openalex.org/W3034702511","https://openalex.org/W3167976421","https://openalex.org/W3206008172","https://openalex.org/W3213575660","https://openalex.org/W4285218990","https://openalex.org/W4286904999","https://openalex.org/W4312466984","https://openalex.org/W4386075783","https://openalex.org/W4394744961","https://openalex.org/W4402754289","https://openalex.org/W4405520428","https://openalex.org/W4408647465","https://openalex.org/W4413147546"],"related_works":[],"abstract_inverted_index":{"Active":[0],"speaker":[1],"detection":[2],"(ASD)":[3],"uses":[4],"visual":[5],"and":[6,33,55,84,99],"audio":[7],"information":[8],"from":[9,60],"raw":[10],"videos":[11],"to":[12,71],"determine":[13],"which":[14],"speakers":[15],"are":[16],"talking":[17],"in":[18,40],"each":[19],"frame.":[20],"The":[21],"majority":[22],"of":[23,38,43,82],"models":[24],"for":[25],"ASD":[26],"have":[27],"been":[28],"large-parameter":[29],"models.":[30],"Recently,":[31],"Light-ASD":[32,54],"LR-ASD":[34,56],"achieved":[35],"a":[36],"reduction":[37],"41X":[39],"the":[41,68,73,79],"number":[42,81],"required":[44,80],"parameters":[45,83,98],"while":[46,77,95],"also":[47],"achieving":[48],"competitive":[49],"performance.":[50],"Yet,":[51],"during":[52],"training,":[53],"can":[57],"often":[58],"suffer":[59],"vanishing":[61,74],"gradients.":[62],"In":[63,86],"this":[64],"paper,":[65],"we":[66],"modify":[67],"original":[69],"architecture":[70],"avoid":[72],"gradient":[75],"problem":[76],"reducing":[78],"FLOPs.":[85,100],"out-of-distribution":[87],"testing,":[88],"our":[89],"proposed":[90],"model":[91],"surpasses":[92],"all":[93],"competitors":[94],"using":[96],"fewer":[97]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-27T00:00:00"}