{"id":"https://openalex.org/W3194051467","doi":"https://doi.org/10.1109/ssp49050.2021.9513767","title":"Multi-Speaker Tracking by Fusing Audio and Video Information","display_name":"Multi-Speaker Tracking by Fusing Audio and Video Information","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3194051467","doi":"https://doi.org/10.1109/ssp49050.2021.9513767","mag":"3194051467"},"language":"en","primary_location":{"id":"doi:10.1109/ssp49050.2021.9513767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp49050.2021.9513767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Statistical Signal Processing Workshop (SSP)","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/A5109456802","display_name":"Zichao Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zichao Xiong","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102001094","display_name":"Hongqing Liu","orcid":"https://orcid.org/0000-0002-2069-0390"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqing Liu","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005083930","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0001-7445-226X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065815971","display_name":"Zhen Luo","orcid":"https://orcid.org/0000-0003-2083-6369"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Luo","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109456802"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.3047,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53806626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"17","issue":null,"first_page":"321","last_page":"325"},"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":0.996999979019165,"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":0.9968000054359436,"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":0.792617917060852},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.6731885075569153},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5921749472618103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5876879692077637},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5352168083190918},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4581126570701599},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4225681722164154},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.400506854057312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3549119830131531},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.2865656614303589},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2009575366973877},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09714937210083008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792617917060852},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.6731885075569153},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5921749472618103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5876879692077637},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5352168083190918},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4581126570701599},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4225681722164154},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.400506854057312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3549119830131531},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2865656614303589},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2009575366973877},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09714937210083008},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssp49050.2021.9513767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp49050.2021.9513767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Statistical Signal Processing Workshop (SSP)","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":21,"referenced_works":["https://openalex.org/W1518556865","https://openalex.org/W1526948613","https://openalex.org/W1908118577","https://openalex.org/W2053101950","https://openalex.org/W2088725063","https://openalex.org/W2129821199","https://openalex.org/W2142612029","https://openalex.org/W2159259269","https://openalex.org/W2166916857","https://openalex.org/W2169195402","https://openalex.org/W2517955251","https://openalex.org/W2551702340","https://openalex.org/W2697319950","https://openalex.org/W2795437830","https://openalex.org/W2884554680","https://openalex.org/W2918984654","https://openalex.org/W2970201661","https://openalex.org/W6631365129","https://openalex.org/W6679546383","https://openalex.org/W6684554773","https://openalex.org/W6684845544"],"related_works":["https://openalex.org/W2100525497","https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329"],"abstract_inverted_index":{"In":[0,100],"this":[1],"work,":[2],"a":[3,18,50,80,154],"novel":[4],"approach":[5],"is":[6,29,47,87,143],"proposed":[7,151],"for":[8],"multi-speaker":[9],"tracking":[10],"by":[11,65,75,89],"integrating":[12],"audio":[13,27,91,110],"and":[14,43,94,113,124,133,161],"visual":[15,45,56,132],"data":[16,126],"in":[17,117,153],"particle":[19,121],"filtering":[20,122],"framework.":[21],"To":[22],"that":[23],"aim,":[24],"first,":[25],"the":[26,33,44,62,67,71,76,83,140,147,150,163],"signal":[28,46],"measured":[30,48],"based":[31],"on":[32,70],"maximum":[34],"Global":[35],"Coherence":[36],"Field":[37,164],"(GCF)":[38],"peak":[39],"at":[40],"each":[41],"frame,":[42],"using":[49],"face":[51,95],"detector.":[52],"Second,":[53],"we":[54,102],"exploit":[55],"observations":[57],"(object":[58],"detections)":[59],"to":[60,107,130,136,145],"guide":[61],"acoustic":[63,68,134],"processing":[64],"constraining":[66],"likelihood":[69,85],"horizontal":[72],"plane":[73],"defined":[74],"predicted":[77],"height":[78],"of":[79,149,156,165],"speaker.":[81],"Moreover,":[82],"video":[84],"function":[86],"improved":[88],"fusing":[90],"positioning":[92,111],"information":[93,112,116],"detection":[96],"3D":[97,114],"mouth":[98,115],"information.":[99],"particular,":[101],"set":[103],"an":[104],"adjustable":[105],"weight":[106],"better":[108],"integrate":[109],"different":[118],"scenes.":[119],"A":[120],"framework":[123],"greedy":[125],"association":[127],"are":[128],"used":[129,144],"incorporate":[131],"likelihoods":[135],"track":[137],"multi-speakers.":[138],"Finally,":[139],"CAV3D":[141],"dataset":[142],"demonstrate":[146],"performance":[148],"method":[152],"variety":[155],"scenarios":[157],"such":[158],"as":[159],"occlusion":[160],"outside":[162],"View":[166],"(FoV).":[167]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}