{"id":"https://openalex.org/W4392903366","doi":"https://doi.org/10.1109/icassp48485.2024.10446460","title":"GLMB 3D Speaker Tracking with Video-Assisted Multi-Channel Audio Optimization Functions","display_name":"GLMB 3D Speaker Tracking with Video-Assisted Multi-Channel Audio Optimization Functions","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903366","doi":"https://doi.org/10.1109/icassp48485.2024.10446460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Qian","raw_affiliation_strings":["University of Science and Technology Beijing,School of Computer and Communication Engineering,China","School of Computer and Communication Engineering, University of Science and Technology Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Computer and Communication Engineering,China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["National University of Singapore,Institute of Data Science,Singapore","Institute of Data Science, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Institute of Data Science,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Institute of Data Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042675934","display_name":"Qiquan Zhang","orcid":"https://orcid.org/0000-0001-5089-6317"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiquan Zhang","raw_affiliation_strings":["University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","School of Electrical Engineering and Telecommunications, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Electrical Engineering and Telecommunications, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056322023","display_name":"Kainan Chen","orcid":"https://orcid.org/0000-0002-7231-2404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kainan Chen","raw_affiliation_strings":["Eigenspace GmbH,Germany","Eigenspace GmbH, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eigenspace GmbH,Germany","institution_ids":[]},{"raw_affiliation_string":"Eigenspace GmbH, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083582801","display_name":"Shoufeng Lin","orcid":"https://orcid.org/0000-0002-9508-0706"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shoufeng Lin","raw_affiliation_strings":["Curtin University,Australia","Curtin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Curtin University,Australia","institution_ids":["https://openalex.org/I205640436"]},{"raw_affiliation_string":"Curtin University, Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2514,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76814557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8100","last_page":"8104"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8268516659736633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.584412693977356},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5473123788833618},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5230634808540344},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5110028982162476},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4200965166091919},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41506391763687134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41364437341690063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268516659736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.584412693977356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5473123788833618},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5230634808540344},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5110028982162476},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4200965166091919},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41506391763687134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41364437341690063},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G6648122539","display_name":null,"funder_award_id":"62306029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"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":23,"referenced_works":["https://openalex.org/W1555217905","https://openalex.org/W1648602279","https://openalex.org/W2033819227","https://openalex.org/W2046317813","https://openalex.org/W2049244691","https://openalex.org/W2088725063","https://openalex.org/W2107493093","https://openalex.org/W2129821199","https://openalex.org/W2129866629","https://openalex.org/W2149900846","https://openalex.org/W2154353836","https://openalex.org/W2167206042","https://openalex.org/W2574583772","https://openalex.org/W2884554680","https://openalex.org/W2890952074","https://openalex.org/W2918984654","https://openalex.org/W2963846200","https://openalex.org/W2970201661","https://openalex.org/W2972568703","https://openalex.org/W3095278226","https://openalex.org/W3176928964","https://openalex.org/W4312367758","https://openalex.org/W6798523648"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W2084086966","https://openalex.org/W200819717","https://openalex.org/W1968065688","https://openalex.org/W2032269556","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W4289829835","https://openalex.org/W107154053"],"abstract_inverted_index":{"Speaker":[0],"tracking":[1,84,127],"plays":[2],"a":[3,20,81,105,113],"significant":[4],"role":[5],"in":[6,23,50,58,97,122],"numerous":[7],"real-world":[8],"human":[9],"robot":[10],"interaction":[11],"(HRI)":[12],"applications.":[13],"In":[14,76],"recent":[15],"years,":[16],"there":[17],"has":[18],"been":[19],"growing":[21],"interest":[22],"utilizing":[24],"multi-sensory":[25],"information,":[26],"such":[27,61],"as":[28,62],"complementary":[29],"audio":[30,101],"and":[31,108,125],"visual":[32,67],"signals,":[33],"to":[34,70],"address":[35],"the":[36,42,53,88,136],"challenges":[37],"of":[38,130],"speaker":[39,83],"tracking.":[40],"Despite":[41],"promising":[43],"results,":[44],"existing":[45],"approaches":[46],"still":[47],"encounter":[48],"difficulties":[49],"accurately":[51],"determining":[52],"speaker\u2019s":[54],"true":[55],"location,":[56],"particularly":[57],"adverse":[59],"conditions":[60],"speech":[63],"pauses,":[64],"reverberation,":[65],"or":[66,73],"occlusions,":[68],"leading":[69],"missed":[71,131],"detections":[72],"spurious":[74],"estimates.":[75],"this":[77],"paper,":[78],"we":[79],"propose":[80],"novel":[82],"method":[85,95],"based":[86],"on":[87,135],"Generalized":[89],"Labelled":[90],"Multi-Bernoulli":[91],"(GLMB)":[92],"filter.":[93],"Our":[94],"operates":[96],"3D":[98],"space":[99],"using":[100],"information":[102],"captured":[103],"by":[104],"microphone":[106],"array":[107],"video":[109],"streams":[110],"obtained":[111],"from":[112],"monocular":[114],"camera.":[115],"The":[116],"GLMB-based":[117],"tracker":[118],"effectively":[119],"handles":[120],"outliers":[121],"location":[123],"estimates":[124],"maintains":[126],"during":[128],"periods":[129],"detections.":[132],"Experiments":[133],"conducted":[134],"publicly":[137],"available":[138],"AV16.3":[139],"dataset":[140],"show":[141],"that":[142],"our":[143],"proposal":[144],"surpasses":[145],"other":[146],"competitive":[147],"methods":[148],"with":[149],"improved":[150],"results.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
