{"id":"https://openalex.org/W4294069529","doi":"https://doi.org/10.1109/icce-taiwan55306.2022.9869193","title":"Automatic Speaker Localization in Conference Based on Yolox-Tiny and TDOA","display_name":"Automatic Speaker Localization in Conference Based on Yolox-Tiny and TDOA","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4294069529","doi":"https://doi.org/10.1109/icce-taiwan55306.2022.9869193"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan55306.2022.9869193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan55306.2022.9869193","pdf_url":null,"source":{"id":"https://openalex.org/S4363607852","display_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","raw_type":"proceedings-article"},"type":"conference-paper","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/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":false,"raw_author_name":"Chen-Chiung Hsieh","raw_affiliation_strings":["Tatung University,Department of Computer Science and Engineering,Taipei,Taiwan","Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tatung University,Department of Computer Science and Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I65196183"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056523755","display_name":"Meng-Ju 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":"Meng-Ju Lu","raw_affiliation_strings":["Tatung University,Department of Computer Science and Engineering,Taipei,Taiwan","Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tatung University,Department of Computer Science and Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I65196183"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028775890","display_name":"You-Zhan Zheng","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":"You-Zhan Zheng","raw_affiliation_strings":["Tatung University,Department of Computer Science and Engineering,Taipei,Taiwan","Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tatung University,Department of Computer Science and Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I65196183"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076370719","display_name":"Hsiao-Ting Tseng","orcid":"https://orcid.org/0000-0001-6652-3363"},"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":["National Central University,Department of Information Management,Taoyuan,Taiwan","Department of Information Management, National Central University, Taoyuan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Central University,Department of Information Management,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]},{"raw_affiliation_string":"Department of Information Management, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09173429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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":0.9933000206947327,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9492999911308289,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9333999752998352,"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":0.901710569858551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7715945243835449},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6783286333084106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5482726693153381},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4906283915042877},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4216369390487671},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4153406620025635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40045008063316345},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12775447964668274}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.901710569858551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715945243835449},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6783286333084106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5482726693153381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4906283915042877},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4216369390487671},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4153406620025635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40045008063316345},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12775447964668274},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan55306.2022.9869193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan55306.2022.9869193","pdf_url":null,"source":{"id":"https://openalex.org/S4363607852","display_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2029938263","https://openalex.org/W2596526952","https://openalex.org/W3184439416"],"related_works":["https://openalex.org/W2380293945","https://openalex.org/W1500522817","https://openalex.org/W1974812937","https://openalex.org/W3095239554","https://openalex.org/W3212409750","https://openalex.org/W1972023576","https://openalex.org/W2072053180","https://openalex.org/W1541088746","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"In":[0],"remote":[1],"conferences,":[2],"it":[3],"is":[4,88,94,105,115],"often":[5],"necessary":[6],"to":[7,44,68,76],"adjust":[8],"the":[9,12,17,22,27,32,40,46,56,60,70,73,78,81,90,96,108,124],"angle":[10],"of":[11,26,30,53,72,80,86,92,98,110],"camera":[13,33,61],"so":[14],"that":[15],"only":[16,99],"speaker's":[18,125],"part":[19],"remains":[20],"in":[21,55,62],"picture.":[23,126],"However,":[24],"most":[25],"current":[28],"methods":[29],"adjusting":[31],"are":[34],"done":[35],"manually.":[36],"This":[37],"study":[38],"uses":[39],"YOLOX-tiny":[41,87],"neural":[42],"network":[43],"detect":[45,69],"mouth":[47],"movements":[48],"and":[49,64,107,113,121],"upper":[50],"body":[51],"positions":[52],"everyone":[54],"picture":[57],"captured":[58],"by":[59],"time,":[63],"cooperates":[65],"with":[66],"TDOA":[67,93],"direction":[71],"sound":[74,114],"source":[75],"enhance":[77],"accuracy":[79],"detection":[82],"results.":[83],"The":[84],"recall":[85,91,97,109],"93%,":[89],"88%,":[95],"using":[100],"video":[101,112],"for":[102],"speaker":[103],"positioning":[104],"77%,":[106],"integrating":[111],"about":[116],"80.3%,":[117],"which":[118],"can":[119],"quickly":[120],"effectively":[122],"retain":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
