{"id":"https://openalex.org/W2141463036","doi":"https://doi.org/10.1109/icassp.2013.6638333","title":"Using The Voice Spectrum For Improved Tracking Of People In A Joint Audio-Video Scheme","display_name":"Using The Voice Spectrum For Improved Tracking Of People In A Joint Audio-Video Scheme","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2141463036","doi":"https://doi.org/10.1109/icassp.2013.6638333","mag":"2141463036"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5083533632","display_name":"Eleonora D'Arca","orcid":null},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eleonora D'Arca","raw_affiliation_strings":["Heriot-Watt University, Edinburgh, Edinburgh, GB","[Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ., Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heriot-Watt University, Edinburgh, Edinburgh, GB","institution_ids":[]},{"raw_affiliation_string":"[Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ., Edinburgh, UK]","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102909686","display_name":"Neil M. Robertson","orcid":"https://orcid.org/0000-0003-2461-8799"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Neil M. Robertson","raw_affiliation_strings":["Joint Research Institute for Signal and Image Processing, Heriot-Watt University & University of Edinburgh, UK","[Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ., Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Research Institute for Signal and Image Processing, Heriot-Watt University & University of Edinburgh, UK","institution_ids":["https://openalex.org/I32062511","https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ., Edinburgh, UK]","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016434897","display_name":"James R. Hopgood","orcid":"https://orcid.org/0000-0002-3029-2425"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Hopgood","raw_affiliation_strings":["Joint Research Institute for Signal and Image Processing, Heriot-Watt University & University of Edinburgh, UK","[Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ., Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Research Institute for Signal and Image Processing, Heriot-Watt University & University of Edinburgh, UK","institution_ids":["https://openalex.org/I32062511","https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Joint Res. Inst. for Signal & Image Process., Heriot-Watt Univ., Edinburgh, UK]","institution_ids":["https://openalex.org/I32062511"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6442,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70975751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2002","issue":null,"first_page":"3622","last_page":"3626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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":0.9939000010490417,"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/scheme","display_name":"Scheme (mathematics)","score":0.7575442790985107},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7574987411499023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750963032245636},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5367822051048279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45767638087272644},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44336411356925964},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4053715169429779},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.38023629784584045},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3280915915966034},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08987227082252502}],"concepts":[{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7575442790985107},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7574987411499023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750963032245636},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5367822051048279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45767638087272644},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44336411356925964},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4053715169429779},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.38023629784584045},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3280915915966034},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08987227082252502},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/1910b03f-5613-48be-8cb8-5833bc24fe94","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/1910b03f-5613-48be-8cb8-5833bc24fe94","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"D'Arca , E , Robertson , N & Hopgood , J 2013 , Using the voice spectrum for improved tracking of people in a joint audio-video scheme . in Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . IEEE International Conference on Acoustics Speech and Signal Processing , Institute of Electrical and Electronics Engineers Inc. , pp. 3622 - 3626 . https://doi.org/10.1109/ICASSP.2013.6638333","raw_type":"bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8726282573","display_name":null,"funder_award_id":"EP/K014277/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W285277413","https://openalex.org/W1591726647","https://openalex.org/W1975143133","https://openalex.org/W2015293542","https://openalex.org/W2024727715","https://openalex.org/W2053150333","https://openalex.org/W2100152238","https://openalex.org/W2124781496","https://openalex.org/W2127025755","https://openalex.org/W2129821199","https://openalex.org/W2129866629","https://openalex.org/W2138414774","https://openalex.org/W2142612029","https://openalex.org/W2143873874","https://openalex.org/W2144467445","https://openalex.org/W2145097187","https://openalex.org/W2147166770","https://openalex.org/W2163141813","https://openalex.org/W2165880886","https://openalex.org/W2407461433","https://openalex.org/W2625987702","https://openalex.org/W2915347754","https://openalex.org/W6635336337","https://openalex.org/W6663730556","https://openalex.org/W6679546383","https://openalex.org/W6681054008","https://openalex.org/W6713775275"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2109142991","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W1546240199","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686"],"abstract_inverted_index":{"In":[0,22],"this":[1,39],"paper":[2],"we":[3,31,58],"present":[4],"a":[5,23,42,115,125],"new":[6],"solution":[7],"to":[8,88],"the":[9,100,119],"problem":[10],"of":[11],"speaker":[12,33,121],"tracking":[13,67,79,102],"among":[14],"people":[15],"where":[16],"occlusions":[17],"occur":[18],"(disappearance":[19],"and":[20,37,57,75,82,93],"non-speaking).":[21],"normal":[24],"conversation":[25],"between":[26],"two":[27],"or":[28],"more":[29],"people,":[30],"learn":[32],"mel-cepstral":[34],"coefficients":[35],"(MFCC)":[36],"incorporate":[38],"information":[40],"into":[41],"sequential":[43],"Bayesian":[44],"audio-video":[45,133],"position":[46],"tracker.":[47],"The":[48],"joint":[49],"video-to-audio":[50],"data":[51,77],"association":[52],"step":[53],"is":[54,127],"thus":[55],"improved":[56,128],"achieve":[59],"robust":[60],"person":[61],"recognition":[62,123],"which":[63],"in":[64,96],"turn":[65],"aids":[66],"performance.":[68],"We":[69],"provide":[70],"comprehensive":[71],"evaluation":[72],"via":[73],"simulations":[74],"real":[76,94],"quoting":[78],"accuracy,":[80],"precision":[81],"diarisation":[83],"error":[84],"rate":[85],"(DER)":[86],"compared":[87],"ground":[89,109],"truth.":[90],"For":[91],"simulate":[92],"experiments":[95],"an":[97],"open":[98],"space":[99],"trajectory":[101],"performance":[103],"increases":[104],"by":[105,129,131],"20%":[106,130],"measured":[107],"against":[108],"truth":[110],"using":[111],"our":[112],"approach.":[113],"As":[114],"further":[116],"enhancement":[117],"versus":[118],"state-of-the-art,":[120],"identity":[122],"at":[124],"distance":[126],"exploiting":[132],"localisation":[134],"cues.":[135]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}