{"id":"https://openalex.org/W4409474124","doi":"https://doi.org/10.1109/jstsp.2025.3560513","title":"$C^{2}$AV-TSE: Context and Confidence-Aware Audio Visual Target Speaker Extraction","display_name":"$C^{2}$AV-TSE: Context and Confidence-Aware Audio Visual Target Speaker Extraction","publication_year":2025,"publication_date":"2025-04-15","ids":{"openalex":"https://openalex.org/W4409474124","doi":"https://doi.org/10.1109/jstsp.2025.3560513"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2025.3560513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3560513","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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":null,"display_name":"Wenxuan Wu","orcid":"https://orcid.org/0009-0001-1235-9729"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenxuan Wu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0001-1235-9729","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108049724","display_name":"Xueyuan Chen","orcid":"https://orcid.org/0000-0003-0493-839X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xueyuan Chen","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["School of Intelligence Science and Technology, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1523-9631","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663491","display_name":"Jiadong Wang","orcid":"https://orcid.org/0000-0001-9372-3133"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jiadong Wang","raw_affiliation_strings":["Technical University of Munich, M&#x00FC;nchen, Germany","Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, M&#x00FC;nchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031382920","display_name":"Lingwei Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lingwei Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9543-1572","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102225156","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4427-3532","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83099297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"4","first_page":"646","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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":0.9958999752998352,"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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537028789520264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5821523666381836},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5819456577301025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5063823461532593},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45250946283340454},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4236750602722168},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37284791469573975},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32594889402389526},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.07531297206878662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537028789520264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5821523666381836},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5819456577301025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5063823461532593},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45250946283340454},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4236750602722168},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37284791469573975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32594889402389526},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.07531297206878662},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3560513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3560513","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2254729389","display_name":null,"funder_award_id":"62401377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2141998673","https://openalex.org/W2802511083","https://openalex.org/W2808631503","https://openalex.org/W2952218014","https://openalex.org/W3007482166","https://openalex.org/W3008400075","https://openalex.org/W3015199127","https://openalex.org/W3015225820","https://openalex.org/W3097450720","https://openalex.org/W3163287738","https://openalex.org/W3163652268","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W4214698081","https://openalex.org/W4225264678","https://openalex.org/W4226021932","https://openalex.org/W4295308317","https://openalex.org/W4372259900","https://openalex.org/W4372260337","https://openalex.org/W4375869294","https://openalex.org/W4385822469","https://openalex.org/W4386066407","https://openalex.org/W4392904258","https://openalex.org/W4394625786","https://openalex.org/W4402352712","https://openalex.org/W6630998832","https://openalex.org/W6742348326","https://openalex.org/W6755207826","https://openalex.org/W6775835775","https://openalex.org/W6780218876","https://openalex.org/W6783838515","https://openalex.org/W6783990618","https://openalex.org/W6789693907","https://openalex.org/W6810168380","https://openalex.org/W6810189000","https://openalex.org/W6840561836","https://openalex.org/W6844194202","https://openalex.org/W6853512485","https://openalex.org/W6858547360"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2131735617","https://openalex.org/W2056912418","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2049538278","https://openalex.org/W2886173746","https://openalex.org/W4200043248"],"abstract_inverted_index":{"Audio-Visual":[0],"Target":[1],"Speaker":[2],"Extraction":[3],"(AV-TSE)":[4],"aims":[5],"to":[6,11,44,102,110,126,134],"mimic":[7],"the":[8,41,67,91,142,159],"human":[9],"ability":[10],"enhance":[12],"auditory":[13],"perception":[14],"using":[15],"visual":[16],"cues.":[17],"Although":[18],"numerous":[19],"models":[20],"have":[21],"been":[22],"proposed":[23,146],"recently,":[24],"most":[25],"of":[26,48,78,144],"them":[27],"estimate":[28],"target":[29,112],"signals":[30],"by":[31],"primarily":[32],"relying":[33],"on":[34,137,158],"local":[35],"dependencies":[36],"within":[37,106,115],"acoustic":[38],"features,":[39],"underutilizing":[40],"human-like":[42],"capacity":[43],"infer":[45],"unclear":[46],"parts":[47,114],"speech":[49],"through":[50],"contextual":[51,100],"information.":[52],"This":[53],"limitation":[54],"results":[55],"in":[56],"not":[57],"only":[58],"suboptimal":[59],"performance":[60,164],"but":[61],"also":[62],"inconsistent":[63],"extraction":[64,107,128,132],"quality":[65,74,129],"across":[66,166],"utterance,":[68],"with":[69],"some":[70],"segments":[71],"exhibiting":[72],"poor":[73],"or":[75],"inadequate":[76],"suppression":[77],"interfering":[79],"speakers.":[80],"To":[81,140],"close":[82],"this":[83],"gap,":[84],"we":[85,118],"propose":[86],"a":[87,120],"model-agnostic":[88,147],"strategy":[89],"called":[90],"Mask-And-Recover":[92],"(MAR).":[93],"It":[94],"integrates":[95],"both":[96],"inter-":[97],"and":[98,130],"intra-modality":[99],"correlations":[101],"enable":[103],"global":[104],"inference":[105],"modules.":[108],"Additionally,":[109],"better":[111],"challenging":[113],"each":[116],"sample,":[117],"introduce":[119],"Fine-grained":[121],"Confidence":[122],"Score":[123],"(FCS)":[124],"model":[125],"assess":[127],"guide":[131],"modules":[133],"emphasize":[135],"improvement":[136],"low-quality":[138],"segments.":[139],"validate":[141],"effectiveness":[143],"our":[145],"training":[148],"paradigm,":[149],"six":[150],"popular":[151],"AV-TSE":[152],"backbones":[153],"were":[154],"adopted":[155],"for":[156],"evaluation":[157],"VoxCeleb2":[160],"dataset,":[161],"demonstrating":[162],"consistent":[163],"improvements":[165],"various":[167],"metrics.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
