{"id":"https://openalex.org/W2610846088","doi":"https://doi.org/10.1109/globalsip.2016.7906033","title":"Active speaker detection in human machine multiparty dialogue using visual prosody information","display_name":"Active speaker detection in human machine multiparty dialogue using visual prosody information","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2610846088","doi":"https://doi.org/10.1109/globalsip.2016.7906033","mag":"2610846088"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2016.7906033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2016.7906033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5043348303","display_name":"Fasih Haider","orcid":"https://orcid.org/0000-0002-5150-3359"},"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":"Fasih Haider","raw_affiliation_strings":["SCSS, Trinity College Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"SCSS, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108471155","display_name":"Nick Campbell","orcid":null},"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":"Nick Campbell","raw_affiliation_strings":["SCSS, Trinity College Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"SCSS, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060851208","display_name":"Saturnino Luz","orcid":"https://orcid.org/0000-0001-8430-7875"},"institutions":[{"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":"Saturnino Luz","raw_affiliation_strings":["IPHSI, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"IPHSI, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043348303"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":1.0087,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.79159224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1207","last_page":"1211"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7995684146881104},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7289918065071106},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6928597688674927},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.688725471496582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6594833135604858},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.6071580648422241},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5773792266845703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5393993258476257},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5249754786491394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995684146881104},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7289918065071106},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6928597688674927},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.688725471496582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6594833135604858},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.6071580648422241},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5773792266845703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5393993258476257},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5249754786491394},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2016.7906033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2016.7906033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W763498075","https://openalex.org/W1542318638","https://openalex.org/W1970027736","https://openalex.org/W1989104072","https://openalex.org/W1999772635","https://openalex.org/W2014621385","https://openalex.org/W2015394094","https://openalex.org/W2054852564","https://openalex.org/W2078813998","https://openalex.org/W2083809740","https://openalex.org/W2104804886","https://openalex.org/W2105101328","https://openalex.org/W2118004237","https://openalex.org/W2133447020","https://openalex.org/W2154636774","https://openalex.org/W2168982238","https://openalex.org/W2171727224","https://openalex.org/W2287407690","https://openalex.org/W2400967734","https://openalex.org/W2476309723","https://openalex.org/W6622346389","https://openalex.org/W6682920111","https://openalex.org/W6685120548","https://openalex.org/W6712911086"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Real-time":[0],"detection":[1,51,98,141],"of":[2,88,126,153],"a":[3,9,23,28,49,63,74],"speaker":[4,43,50,94,109,148],"and":[5,33,44,59,86,90,95,111,124,128,142,151],"speaker's":[6],"location":[7],"is":[8,13,22,71],"challenging":[10],"task,":[11],"which":[12],"usually":[14],"addressed":[15],"by":[16],"processing":[17],"acoustic/visual":[18],"information.":[19],"However,":[20,113],"it":[21,114],"well-known":[24],"fact":[25],"that":[26,134],"when":[27],"person":[29],"speaks,":[30],"the":[31,42,117,122,135],"lip":[32,60,91,118,129,144],"head":[34,58,84,89,123,127,136],"movements":[35,92,137,145],"can":[36],"also":[37,115],"be":[38],"used":[39],"to":[40],"detect":[41],"location.":[45],"This":[46,69],"paper":[47,80],"proposes":[48],"system":[52],"using":[53],"visual":[54],"prosody":[55],"information":[56],"(e.g.":[57],"movements)":[61],"in":[62,99,147],"human-machine":[64,75],"multiparty":[65,76],"interactive":[66],"dialogue":[67,77],"setting.":[68],"analysis":[70],"performed":[72],"on":[73,83],"corpora.":[78],"The":[79,131],"reports":[81],"results":[82,120,132],"movement":[85,119],"fusion":[87,152],"for":[93],"speech":[96],"activity":[97],"three":[100],"different":[101],"machine":[102],"learning":[103],"model":[104],"training":[105],"settings":[106],"(speaker":[107],"dependent,":[108],"independent":[110,149],"hybrid).":[112],"compares":[116],"with":[121],"`fusion":[125],"movements'.":[130],"show":[133],"contributes":[138],"significantly":[139],"towards":[140],"outperform":[143],"except":[146],"settings,":[150],"both":[154],"improves":[155],"performance.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
