{"id":"https://openalex.org/W4406745262","doi":"https://doi.org/10.1109/wacv61042.2026.00704","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","display_name":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4406745262","doi":"https://doi.org/10.1109/wacv61042.2026.00704"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.11899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111621798","display_name":"Le T. Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Le Thien Phuc Nguyen","raw_affiliation_strings":["University of Wisconsin,Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin,Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102905674","display_name":"Zhuoran Yu","orcid":"https://orcid.org/0009-0005-0173-0907"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Yu","raw_affiliation_strings":["University of Wisconsin,Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin,Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112702739","display_name":"Yong Jae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Jae Lee","raw_affiliation_strings":["University of Wisconsin,Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin,Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111621798"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00736454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7291","last_page":"7300"},"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/T11448","display_name":"Face recognition and analysis","score":0.9684000015258789,"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/robustness","display_name":"Robustness (evolution)","score":0.7471836805343628},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.743959367275238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5035478472709656},{"id":"https://openalex.org/keywords/laser","display_name":"Laser","score":0.47107329964637756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4273563623428345},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3928128182888031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34461337327957153},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.10625976324081421},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09365496039390564},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08923757076263428}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7471836805343628},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.743959367275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5035478472709656},{"id":"https://openalex.org/C520434653","wikidata":"https://www.wikidata.org/wiki/Q38867","display_name":"Laser","level":2,"score":0.47107329964637756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4273563623428345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3928128182888031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34461337327957153},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.10625976324081421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09365496039390564},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08923757076263428},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.11899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.11899","pdf_url":"https://arxiv.org/pdf/2501.11899","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.11899","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.11899","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.11899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.11899","pdf_url":"https://arxiv.org/pdf/2501.11899","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6216891907","display_name":null,"funder_award_id":"IIS2404180","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7290345477","display_name":null,"funder_award_id":"2022-0-00871","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8608246966","display_name":null,"funder_award_id":"2022-0-00871","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406745262.pdf","grobid_xml":"https://content.openalex.org/works/W4406745262.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2026924879","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W2052388267","https://openalex.org/W2950647290","https://openalex.org/W2620829895","https://openalex.org/W2356918560","https://openalex.org/W4243161226"],"abstract_inverted_index":{"Active":[0],"Speaker":[1,43],"Detection":[2],"(ASD)":[3],"aims":[4],"to":[5,55,60,163],"identify":[6],"who":[7],"is":[8],"speaking":[9],"in":[10,124],"complex":[11],"visual":[12,69],"scenes.":[13],"While":[14],"humans":[15],"naturally":[16],"rely":[17],"on":[18],"lip-audio":[19],"synchronization,":[20],"existing":[21],"ASD":[22],"models":[23,113],"often":[24],"misclassify":[25],"non-speaking":[26],"instances":[27],"when":[28],"lip":[29,51,74],"movements":[30],"and":[31,71,98,117,152,157],"audio":[32],"are":[33],"unsynchronized.":[34],"To":[35,79,120],"address":[36],"this,":[37],"we":[38,89,127],"propose":[39],"Lip":[40],"landmark":[41,105],"Assisted":[42],"dEtection":[44],"for":[45,104],"Robustness":[46],"(LASER),":[47],"which":[48],"explicitly":[49],"incorporates":[50],"landmarks":[52,75],"during":[53],"training":[54],"guide":[56],"the":[57,102,144],"model\u2019s":[58],"attention":[59],"speech-relevant":[61],"regions.":[62],"Given":[63],"a":[64,130],"face":[65],"track,":[66],"LASER":[67,110,147],"extracts":[68],"features":[70],"encodes":[72],"2D":[73],"into":[76],"dense":[77],"maps.":[78],"handle":[80],"failure":[81],"cases":[82],"such":[83],"as":[84],"low":[85],"resolution":[86],"or":[87],"occlusion,":[88],"introduce":[90,128],"an":[91],"auxiliary":[92],"consistency":[93],"loss":[94],"that":[95],"aligns":[96],"lip-aware":[97],"face-only":[99],"predictions,":[100],"removing":[101],"need":[103],"detectors":[106],"at":[107],"test":[108],"time.":[109],"outperforms":[111],"state-of-the-art":[112],"across":[114],"both":[115],"in-domain":[116],"out-of-domain":[118],"benchmarks.":[119],"further":[121],"evaluate":[122],"robustness":[123],"realistic":[125],"conditions,":[126],"LASER-bench,":[129],"curated":[131],"dataset":[132],"of":[133,140],"modern":[134],"video":[135],"clips":[136],"with":[137],"varying":[138],"levels":[139],"background":[141],"noise.":[142],"On":[143],"high-noise":[145],"subset,":[146],"improves":[148],"mAP":[149],"by":[150],"3.3":[151],"4.3":[153],"points":[154],"over":[155],"LoCoNet":[156],"TalkNet,":[158],"respectively,":[159],"demonstrating":[160],"strong":[161],"resilience":[162],"real-world":[164],"acoustic":[165],"challenges.":[166]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-10-10T00:00:00"}