{"id":"https://openalex.org/W1994379197","doi":"https://doi.org/10.1109/icics.2011.6173618","title":"Audiovisual speaker localization in medium smart meeting room","display_name":"Audiovisual speaker localization in medium smart meeting room","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W1994379197","doi":"https://doi.org/10.1109/icics.2011.6173618","mag":"1994379197"},"language":"en","primary_location":{"id":"doi:10.1109/icics.2011.6173618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icics.2011.6173618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 8th International Conference on Information, Communications &amp; 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/A5007008031","display_name":"Andrey Ronzhin","orcid":"https://orcid.org/0000-0002-8903-3508"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"A. Ronzhin","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007008031","display_name":"Andrey Ronzhin","orcid":"https://orcid.org/0000-0002-8903-3508"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A. Ronzhin","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067985539","display_name":"Victor Budkov","orcid":"https://orcid.org/0000-0003-4795-4998"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"V. Budkov","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007008031"],"corresponding_institution_ids":["https://openalex.org/I4210103826"],"apc_list":null,"apc_paid":null,"fwci":0.3062,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.51939583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9876000285148621,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.975600004196167,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7573719024658203},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7569459676742554},{"id":"https://openalex.org/keywords/source-tracking","display_name":"Source tracking","score":0.6581375598907471},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.6523240208625793},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5628871321678162},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5378315448760986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.515040397644043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4659489393234253},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4198344945907593},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.41447919607162476},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1773153841495514},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16756463050842285},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.07154738903045654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573719024658203},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7569459676742554},{"id":"https://openalex.org/C2779167275","wikidata":"https://www.wikidata.org/wiki/Q7565165","display_name":"Source tracking","level":2,"score":0.6581375598907471},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.6523240208625793},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5628871321678162},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5378315448760986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.515040397644043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659489393234253},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4198344945907593},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.41447919607162476},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1773153841495514},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16756463050842285},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.07154738903045654},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icics.2011.6173618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icics.2011.6173618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 8th International Conference on Information, Communications &amp; Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"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":17,"referenced_works":["https://openalex.org/W259522375","https://openalex.org/W1512868774","https://openalex.org/W1555217905","https://openalex.org/W1580141537","https://openalex.org/W1781788938","https://openalex.org/W1786709202","https://openalex.org/W1821174601","https://openalex.org/W1992825118","https://openalex.org/W2098473789","https://openalex.org/W2101357796","https://openalex.org/W2104804886","https://openalex.org/W2118869960","https://openalex.org/W2157667843","https://openalex.org/W2168185689","https://openalex.org/W3151111735","https://openalex.org/W4210849719","https://openalex.org/W4249042830"],"related_works":["https://openalex.org/W2085333312","https://openalex.org/W2098651198","https://openalex.org/W2163346880","https://openalex.org/W1981446207","https://openalex.org/W3008382217","https://openalex.org/W1973916163","https://openalex.org/W1988435165","https://openalex.org/W2543820188","https://openalex.org/W2783367817","https://openalex.org/W3150130840"],"abstract_inverted_index":{"The":[0],"issue":[1],"of":[2,5,24,37,48,56,88],"automatic":[3],"selection":[4],"the":[6,17,41,89,97,101],"current":[7],"active":[8],"speaker":[9,38,64,90],"among":[10],"more":[11],"than":[12],"thirty":[13],"participants":[14,57],"located":[15],"in":[16,40,58],"medium-sized":[18],"meeting":[19,44],"room":[20],"is":[21,84],"considered.":[22],"Techniques":[23],"video":[25],"tracking":[26,62],"and":[27,69,109],"sound":[28,77,102],"source":[29,78,103],"localization":[30,79,104],"are":[31],"implemented":[32],"for":[33,54,73,86],"recording":[34],"AVI":[35],"files":[36],"remarks":[39],"developed":[42],"smart":[43],"room.":[45],"Video":[46],"processing":[47],"streams":[49],"from":[50],"five":[51],"cameras":[52],"serves":[53],"registration":[55],"fixed":[59],"chair":[60],"positions,":[61],"main":[63],"based":[65,80],"on":[66,81],"histogram":[67],"comparison":[68],"AdaBoosted":[70],"cascade":[71],"classifier":[72],"face":[74],"detection.":[75],"Multichannel":[76],"GCC-PHAT":[82],"method":[83],"used":[85],"estimation":[87],"position":[91],"by":[92],"four":[93],"microphone":[94],"arrays.":[95],"In":[96],"18dB":[98],"SNR":[99],"case":[100],"rate":[105],"was":[106,112],"about":[107],"97%":[108],"fine":[110],"RMSE":[111],"lower":[113],"0.23":[114],"m.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
