{"id":"https://openalex.org/W4383722784","doi":"https://doi.org/10.3390/s23146250","title":"Automatic Speaker Positioning in Meetings Based on YOLO and TDOA","display_name":"Automatic Speaker Positioning in Meetings Based on YOLO and TDOA","publication_year":2023,"publication_date":"2023-07-08","ids":{"openalex":"https://openalex.org/W4383722784","doi":"https://doi.org/10.3390/s23146250","pmid":"https://pubmed.ncbi.nlm.nih.gov/37514545"},"language":"en","primary_location":{"id":"doi:10.3390/s23146250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23146250","pdf_url":"https://www.mdpi.com/1424-8220/23/14/6250/pdf?version=1688809048","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/14/6250/pdf?version=1688809048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041417678","display_name":"Chen-Chiung Hsieh","orcid":"https://orcid.org/0000-0002-7716-7306"},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chen-Chiung Hsieh","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei City 104, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-7716-7306","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei City 104, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114065446","display_name":"Men-Ru Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Men-Ru Lu","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei City 104, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei City 104, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015415097","display_name":"Hsiao\u2010Ting Tseng","orcid":"https://orcid.org/0000-0002-8289-5236"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiao-Ting Tseng","raw_affiliation_strings":["Department of Information Management, National Central University, Taoyuan City 320, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8289-5236","affiliations":[{"raw_affiliation_string":"Department of Information Management, National Central University, Taoyuan City 320, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041417678"],"corresponding_institution_ids":["https://openalex.org/I65196183"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.1954,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42912953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"23","issue":"14","first_page":"6250","last_page":"6250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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":0.9921000003814697,"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/multilateration","display_name":"Multilateration","score":0.9068679809570312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6451192498207092},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5556899905204773},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5370921492576599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5102701187133789},{"id":"https://openalex.org/keywords/geographic-coordinate-system","display_name":"Geographic coordinate system","score":0.5016486644744873},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.49106764793395996},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4254446029663086},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.31605812907218933},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22657617926597595},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1797126829624176},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1661471724510193},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.13737979531288147},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09126028418540955},{"id":"https://openalex.org/keywords/geodesy","display_name":"Geodesy","score":0.09100133180618286}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.9068679809570312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6451192498207092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5556899905204773},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5370921492576599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102701187133789},{"id":"https://openalex.org/C123046963","wikidata":"https://www.wikidata.org/wiki/Q22664","display_name":"Geographic coordinate system","level":2,"score":0.5016486644744873},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.49106764793395996},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4254446029663086},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.31605812907218933},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22657617926597595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1797126829624176},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1661471724510193},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.13737979531288147},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09126028418540955},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.09100133180618286},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008593","descriptor_name":"Menopause","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008593","descriptor_name":"Menopause","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008593","descriptor_name":"Menopause","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058872","descriptor_name":"Epidemics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058872","descriptor_name":"Epidemics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058872","descriptor_name":"Epidemics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s23146250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23146250","pdf_url":"https://www.mdpi.com/1424-8220/23/14/6250/pdf?version=1688809048","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:37514545","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37514545","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10384276","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10384276","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10384276/pdf/sensors-23-06250.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:7dd030d02979451cb427d94463acec5c","is_oa":true,"landing_page_url":"https://doaj.org/article/7dd030d02979451cb427d94463acec5c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 14, p 6250 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/14/6250/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23146250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 14; Pages: 6250","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23146250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23146250","pdf_url":"https://www.mdpi.com/1424-8220/23/14/6250/pdf?version=1688809048","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4383722784.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1483870316","https://openalex.org/W1536680647","https://openalex.org/W2060108923","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2570343428","https://openalex.org/W2943934283","https://openalex.org/W3011652020","https://openalex.org/W3089134182","https://openalex.org/W3132830522","https://openalex.org/W4214613382","https://openalex.org/W4280603059","https://openalex.org/W6620707391","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W1975886381","https://openalex.org/W2360764675","https://openalex.org/W43236265","https://openalex.org/W2188292175","https://openalex.org/W94382153","https://openalex.org/W4280569619","https://openalex.org/W202339627","https://openalex.org/W2130253519","https://openalex.org/W2007425937","https://openalex.org/W3214148829"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"many":[3],"things":[4],"have":[5],"been":[6],"held":[7],"via":[8],"video":[9],"conferences":[10],"due":[11],"to":[12,47,58,91,108,131],"the":[13,16,20,33,36,45,48,54,60,67,80,83,93,96,100,109,113,117,120,123,126,133,136,139,146,150,153,156,161,173,183,197,202,208,213,221],"impact":[14],"of":[15,63,86,95,155,176,186],"COVID-19":[17],"epidemic":[18],"around":[19],"world.":[21],"A":[22],"webcam":[23],"will":[24],"be":[25],"used":[26,90,130],"in":[27,112,216],"conjunction":[28],"with":[29],"a":[30,226],"computer":[31],"and":[32,42,69,122,138,152,182,193,207,223],"Internet.":[34],"However,":[35],"network":[37],"camera":[38,140],"cannot":[39,43],"automatically":[40],"turn":[41],"lock":[44],"screen":[46,68],"speaker.":[49],"Therefore,":[50,212],"this":[51,217],"study":[52,218],"uses":[53],"objection":[55],"detector":[56],"YOLO":[57,105],"capture":[59],"upper":[61],"body":[62],"all":[64],"people":[65],"on":[66],"judge":[70],"whether":[71],"each":[72],"person":[73,121,137],"opens":[74],"or":[75],"closes":[76],"their":[77],"mouth.":[78],"At":[79],"same":[81],"time,":[82],"Time":[84],"Difference":[85],"Arrival":[87],"(TDOA)":[88],"is":[89,106],"detect":[92],"angle":[94,134,147,154],"sound":[97,157],"source.":[98,233],"Finally,":[99,145],"person's":[101,110],"position":[102,111],"obtained":[103,148,159],"by":[104,149,160],"reversed":[107],"spatial":[114,127],"coordinates":[115,128],"through":[116,141,178],"distance":[118],"between":[119,135],"camera.":[124],"Then,":[125],"are":[129,164],"calculate":[132],"inverse":[142],"trigonometric":[143],"functions.":[144],"camera,":[151],"source":[158],"microphone":[162],"array,":[163],"matched":[165],"for":[166,195],"positioning.":[167],"The":[168],"experimental":[169],"results":[170],"show":[171],"that":[172],"recall":[174,184,198],"rate":[175,185,199,204],"positioning":[177],"YOLOX-Tiny":[179,192],"reached":[180,189,200,205,210],"85.2%,":[181],"TDOA":[187,194],"alone":[188],"88%.":[190],"Integrating":[191],"positioning,":[196],"86.7%,":[201],"precision":[203],"100%,":[206],"accuracy":[209],"94.5%.":[211],"method":[214],"proposed":[215],"can":[219],"locate":[220],"speaker,":[222],"it":[224],"has":[225],"better":[227],"effect":[228],"than":[229],"using":[230],"only":[231],"one":[232]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
