{"id":"https://openalex.org/W4375868954","doi":"https://doi.org/10.1109/icassp49357.2023.10095549","title":"Incorporating Lip Features into Audio-Visual Multi-Speaker DOA Estimation by Gated Fusion","display_name":"Incorporating Lip Features into Audio-Visual Multi-Speaker DOA Estimation by Gated Fusion","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868954","doi":"https://doi.org/10.1109/icassp49357.2023.10095549"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038529708","display_name":"Ya Jiang","orcid":"https://orcid.org/0000-0003-1733-8887"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Jiang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442517","display_name":"Hang Chen","orcid":"https://orcid.org/0009-0008-7585-033X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4833,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56244142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":1.0,"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":1.0,"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":0.9976000189781189,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9905999898910522,"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":0.8031885623931885},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7449691891670227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6482086777687073},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5994910597801208},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5948213338851929},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4689585268497467},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4547433853149414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4398627281188965},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4155520796775818},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.41501277685165405},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37600177526474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37383943796157837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031885623931885},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7449691891670227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6482086777687073},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5994910597801208},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5948213338851929},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4689585268497467},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4547433853149414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4398627281188965},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4155520796775818},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.41501277685165405},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37600177526474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37383943796157837},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2011396567","https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2114219351","https://openalex.org/W2128970593","https://openalex.org/W2222512263","https://openalex.org/W2551990143","https://openalex.org/W2810934215","https://openalex.org/W2903040254","https://openalex.org/W2964342924","https://openalex.org/W2977809668","https://openalex.org/W3011890046","https://openalex.org/W3016011581","https://openalex.org/W3035449864","https://openalex.org/W3081461453","https://openalex.org/W3168662520","https://openalex.org/W3198730349","https://openalex.org/W4221162997","https://openalex.org/W4226301259","https://openalex.org/W4249477935","https://openalex.org/W4293363567","https://openalex.org/W4297841387","https://openalex.org/W4312356258","https://openalex.org/W4319780182","https://openalex.org/W6726497184","https://openalex.org/W6941384618"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"The":[0,92],"audio-visual":[1,19],"direction":[2],"of":[3,55,71,110,156,162],"arrival":[4],"(DOA)":[5],"estimation":[6,22,106],"has":[7],"demonstrated":[8],"superior":[9],"performance":[10],"recently.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15,42],"present":[16],"a":[17,80],"novel":[18],"multi-speaker":[20,30,167],"DOA":[21,105],"network,":[23],"which":[24],"for":[25],"the":[26,35,44,48,52,60,68,90,98,103,108,111,117,129,136,140,151,160,163],"first":[27],"time":[28],"incorporates":[29],"lip":[31,53],"features":[32],"to":[33,63,85,89,97,101,135],"adapt":[34],"complex":[36],"overlapping":[37],"and":[38,51,75,116,154],"noisy":[39],"scenarios.":[40,168],"Firstly,":[41],"encode":[43],"multi-channel":[45],"audio":[46],"features,":[47],"reference":[49],"angles":[50,74],"Regions":[54],"Interest":[56],"(RoIs)":[57],"detected":[58],"from":[59],"video":[61],"respectively":[62],"acquire":[64],"high-level":[65],"representations.":[66],"Then":[67],"multi-modal":[69],"embeddings":[70],"audio,":[72],"speaker":[73,113,118],"lips":[76],"are":[77],"fused":[78,93],"by":[79,132],"tri-modal":[81],"gated":[82],"fusion":[83],"module":[84],"balance":[86],"their":[87],"contributions":[88],"output.":[91],"embedding":[94],"is":[95],"sent":[96],"backend":[99],"network":[100],"obtain":[102],"accurate":[104],"with":[107],"combination":[109],"predicted":[112],"angular":[114],"vectors":[115],"activities.":[119],"Experimental":[120],"results":[121,158],"show":[122],"that":[123],"our":[124],"proposed":[125,164],"approach":[126],"can":[127],"reduce":[128],"localization":[130,157],"error":[131],"73.48%":[133],"compared":[134],"previous":[137],"work":[138],"on":[139],"2021":[141],"Multi-modal":[142],"Information":[143],"based":[144],"Speech":[145],"Processing":[146],"(MISP)":[147],"Challenge":[148],"corpus.":[149],"Meanwhile,":[150],"high":[152],"accuracy":[153],"stability":[155],"demonstrate":[159],"robustness":[161],"model":[165],"in":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
