{"id":"https://openalex.org/W2142683365","doi":"https://doi.org/10.1109/icassp.2011.5946941","title":"Voxel-based Viterbi Active Speaker Tracking (V-VAST) with best view selection for video lecture post-production","display_name":"Voxel-based Viterbi Active Speaker Tracking (V-VAST) with best view selection for video lecture post-production","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2142683365","doi":"https://doi.org/10.1109/icassp.2011.5946941","mag":"2142683365"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102719208","display_name":"Damien P. Kelly","orcid":"https://orcid.org/0000-0001-7423-4801"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Damien Kelly","raw_affiliation_strings":["Sigmedia Group, School of Engineering, Trinity College Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Sigmedia Group, School of Engineering, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073540444","display_name":"Anil Kokaram","orcid":"https://orcid.org/0000-0001-5304-6238"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Anil Kokaram","raw_affiliation_strings":["Sigmedia Group, School of Engineering, Trinity College Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Sigmedia Group, School of Engineering, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045166071","display_name":"Frank Boland","orcid":"https://orcid.org/0000-0002-9599-5244"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Frank Boland","raw_affiliation_strings":["Sigmedia Group, School of Engineering, Trinity College Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Sigmedia Group, School of Engineering, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102719208"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":0.6125,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68707166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"2296","last_page":"2299"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9936000108718872,"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/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.8644431829452515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190022706985474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6203022599220276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5971720814704895},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5763680338859558},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5464304089546204},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.5401971936225891},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.508761465549469},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.4875935912132263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3213408291339874},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3203352689743042},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2325347363948822}],"concepts":[{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.8644431829452515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190022706985474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6203022599220276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5971720814704895},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5763680338859558},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5464304089546204},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.5401971936225891},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.508761465549469},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4875935912132263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3213408291339874},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3203352689743042},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2325347363948822},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5946941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1537690864","https://openalex.org/W2031664991","https://openalex.org/W2033819227","https://openalex.org/W2046317813","https://openalex.org/W2047867038","https://openalex.org/W2100152238","https://openalex.org/W2128129709","https://openalex.org/W2142511364","https://openalex.org/W6678907557"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2386035178"],"abstract_inverted_index":{"An":[0],"automated":[1],"system":[2,25,100],"is":[3,47,56,76,85],"presented":[4],"for":[5,49],"reducing":[6],"a":[7,12,17,61],"multi-view":[8],"lecture":[9],"recording":[10],"into":[11],"single":[13],"view":[14,19,112],"video":[15],"containing":[16],"best":[18],"summary":[20],"of":[21,63,93,113],"active":[22,65,115],"speakers.":[23],"The":[24,53],"uses":[26],"skin":[27],"color":[28],"detection":[29],"and":[30,84],"voxel-based":[31],"analysis":[32],"in":[33],"locating":[34],"likely":[35],"speaker":[36,51,66,116],"locations.":[37],"Using":[38,95],"time-delay":[39],"estimates":[40],"from":[41,103],"multiple":[42],"micro":[43],"phones,":[44],"speech":[45,71],"activity":[46],"analyzed":[48],"each":[50],"position.":[52],"Viterbi":[54,79],"algorithm":[55],"then":[57,101],"used":[58],"to":[59,87,117],"estimate":[60],"track":[62,88],"the":[64,69,96,99,104,108,114],"which":[67],"maximizes":[68],"observed":[70],"activity.":[72],"This":[73],"novel":[74],"approach":[75],"termed":[77],"Voxel-based":[78],"Active":[80],"Speaker":[81],"Tracking":[82],"(V-VAST)":[83],"shown":[86],"speakers":[89],"with":[90],"an":[91],"accuracy":[92],"0.23m.":[94],"tracking":[97],"information,":[98],"extracts":[102],"available":[105],"camera":[106],"views":[107],"most":[109],"frontal":[110],"face":[111],"display.":[118]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}