{"id":"https://openalex.org/W4408353839","doi":"https://doi.org/10.1109/icassp49660.2025.10889368","title":"Audio-Faces Intra-Frame Alignment with Graph Attention Networks for Active Speaker Detection","display_name":"Audio-Faces Intra-Frame Alignment with Graph Attention Networks for Active Speaker Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353839","doi":"https://doi.org/10.1109/icassp49660.2025.10889368"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889368","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/A5100580962","display_name":"Yongkang Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongkang Yin","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564433","display_name":"Xusheng Yang","orcid":"https://orcid.org/0009-0001-3790-1238"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xusheng Yang","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017770233","display_name":"Liming Liang","orcid":"https://orcid.org/0000-0003-4549-4414"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Liang","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699660","display_name":"Li Xu","orcid":"https://orcid.org/0000-0003-2954-3271"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Tencent PCG,ARC Lab,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034401157","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0002-0144-1794"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100580962"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75604013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9955000281333923,"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":0.9894999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8108718991279602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6142945885658264},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5348445773124695},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46168842911720276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40951111912727356},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12649500370025635},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11953875422477722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108718991279602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6142945885658264},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5348445773124695},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46168842911720276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40951111912727356},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12649500370025635},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11953875422477722}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889368","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2330149154","https://openalex.org/W2551572271","https://openalex.org/W2963608065","https://openalex.org/W2981087920","https://openalex.org/W2985331920","https://openalex.org/W3016098309","https://openalex.org/W3034702511","https://openalex.org/W3136499730","https://openalex.org/W3169351047","https://openalex.org/W3172472082","https://openalex.org/W3189964604","https://openalex.org/W3206008172","https://openalex.org/W4214701094","https://openalex.org/W4225302874","https://openalex.org/W4286378963","https://openalex.org/W4291920479","https://openalex.org/W4312268709","https://openalex.org/W4312319640","https://openalex.org/W4312466984","https://openalex.org/W4386075783","https://openalex.org/W4392908938","https://openalex.org/W4402111956","https://openalex.org/W4402754289","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6739901393","https://openalex.org/W6745537798"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Audio-Visual":[0],"Active":[1],"Speaker":[2],"Detection(ASD)":[3],"is":[4,14,132,168],"the":[5,44,49,53,57,68,78,95,114,117,137,140,148,151,154,158,162,164,172,201],"task":[6],"of":[7,59,88,97,153],"identifying,":[8],"at":[9],"any":[10],"given":[11],"moment,":[12],"who":[13],"actively":[15],"speaking":[16],"in":[17,56,77,104],"a":[18,109,123],"multi-person":[19],"scene":[20],"by":[21],"using":[22,122],"audio":[23,34,118,141],"and":[24,35,94,119,142,146,212],"visual":[25],"cues.":[26],"Current":[27],"main":[28],"stream":[29],"ASD":[30],"methods":[31],"separately":[32],"encode":[33],"facial":[36,50],"features,":[37],"then":[38],"adopt":[39,108],"post-feature":[40],"fusion":[41],"approach":[42,207],"where":[43],"acoustic":[45],"features":[46,51,187,195],"fused":[47],"with":[48,166,196],"from":[52],"same":[54,159],"frame":[55,79],"manner":[58],"vector":[60],"concatenating":[61],"or":[62,80],"simple":[63],"projecting.":[64],"Such":[65],"solution":[66,111],"faces":[67,76,152],"challenges":[69],"when":[70],"there":[71,85],"are":[72,86],"more":[73],"than":[74],"one":[75],"overlapping":[81],"speeches":[82],"occur":[83],"since":[84],"lack":[87],"information":[89,121],"alignment":[90],"between":[91,116,139,150,176],"active":[92],"speech":[93,186],"face":[96,120],"taking":[98],"person.":[99],"Based":[100],"on":[101],"this":[102,105],"observation,":[103],"study,":[106],"we":[107,128,180],"new":[110],"to":[112,134,170,189],"establish":[113],"relationships":[115,138],"heterogeneous":[124],"graph":[125,165],"explicitly.":[126],"Specifically,":[127],"propose":[129],"AFs-Net,":[130],"which":[131],"able":[133],"capture":[135],"both":[136,209],"each":[143],"candidate\u2019s":[144],"face,":[145],"also":[147],"interactions":[149],"candidates":[155],"themselves":[156],"within":[157],"intra-frame.":[160],"As":[161],"result,":[163],"attention":[167],"trained":[169],"learn":[171],"importance":[173],"(attention":[174],"coefficient)":[175],"adjacent":[177],"nodes.":[178],"Additionally,":[179],"impose":[181],"consistency":[182],"constraints":[183],"that":[184,217],"bring":[185],"closer":[188],"speaker":[190],"characteristics,":[191,198],"while":[192],"aligning":[193],"non-speech":[194],"non-speaker":[197],"further":[199],"enhancing":[200],"audio-faces":[202],"alignment.":[203],"Our":[204],"frame-level":[205],"modeling":[206],"supports":[208],"streaming":[210],"applications":[211],"real-time":[213],"operation.":[214],"Experiments":[215],"show":[216],"our":[218],"method":[219],"achieves":[220],"state-of-the-art":[221],"(SOTA)":[222],"performance":[223],"across":[224],"multiple":[225],"datasets.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}