{"id":"https://openalex.org/W2205838157","doi":"https://doi.org/10.1109/iros.2015.7354167","title":"Speech activity detection and face orientation estimation using multiple microphone arrays and human position information","display_name":"Speech activity detection and face orientation estimation using multiple microphone arrays and human position information","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2205838157","doi":"https://doi.org/10.1109/iros.2015.7354167","mag":"2205838157"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2015.7354167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos T. Ishi","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Labs., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Labs., Kyoto, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033160141","display_name":"Jani Even","orcid":"https://orcid.org/0000-0003-0743-5384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jani Even","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Labs, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Labs, Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058513264","display_name":"Norihiro Hagita","orcid":"https://orcid.org/0000-0001-8007-4701"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norihiro Hagita","raw_affiliation_strings":["Intelligent Robotics and Communication Labs, ATR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Robotics and Communication Labs, ATR","institution_ids":["https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"5574","last_page":"5579"},"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/T11448","display_name":"Face recognition and analysis","score":0.989300012588501,"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":0.988099992275238,"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/orientation","display_name":"Orientation (vector space)","score":0.812118649482727},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.8049753904342651},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269671559333801},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.7072052955627441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5935811996459961},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5865579843521118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5627113580703735},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.532808780670166},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.49978113174438477},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.42925602197647095},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.3842068016529083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3348742425441742},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.18803361058235168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12545788288116455},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0793379545211792},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06696411967277527},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.05671817064285278}],"concepts":[{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.812118649482727},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8049753904342651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269671559333801},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.7072052955627441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5935811996459961},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5865579843521118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627113580703735},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.532808780670166},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.49978113174438477},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.42925602197647095},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3842068016529083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3348742425441742},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.18803361058235168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12545788288116455},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0793379545211792},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06696411967277527},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.05671817064285278},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2015.7354167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W253649471","https://openalex.org/W1553305517","https://openalex.org/W1981753630","https://openalex.org/W2016565202","https://openalex.org/W2067192547","https://openalex.org/W2123132313","https://openalex.org/W2144155486","https://openalex.org/W2149264547","https://openalex.org/W2149986665","https://openalex.org/W2151227854","https://openalex.org/W2158419246","https://openalex.org/W2168483376","https://openalex.org/W2171355909","https://openalex.org/W6684756010"],"related_works":["https://openalex.org/W53042703","https://openalex.org/W2080594779","https://openalex.org/W2378555553","https://openalex.org/W2375878039","https://openalex.org/W2741165524","https://openalex.org/W2368198420","https://openalex.org/W3101807488","https://openalex.org/W2004195487","https://openalex.org/W2390289544","https://openalex.org/W2910627863"],"abstract_inverted_index":{"We":[0,22],"developed":[1,37],"a":[2,25],"system":[3,38,63],"for":[4,27],"detecting":[5],"the":[6,29,33,61,87,94,98],"speech":[7,66],"activity":[8,67],"intervals":[9,68],"of":[10,32,73],"multiple":[11,15,55],"speakers":[12],"by":[13,54],"combining":[14],"microphone":[16],"arrays":[17,91],"and":[18,49,51,75],"human":[19],"tracking":[20],"technologies.":[21],"also":[23],"proposed":[24,62],"method":[26],"estimating":[28],"face":[30,76,100],"orientation":[31],"detected":[34],"speakers.":[35,56],"The":[36],"was":[39],"evaluated":[40],"in":[41,46,84,93],"two":[42],"steps:":[43],"individual":[44],"utterances":[45],"different":[47],"positions":[48],"orientations;":[50],"simultaneous":[52],"dialogues":[53],"Evaluation":[57],"results":[58],"revealed":[59],"that":[60],"could":[64],"detect":[65],"with":[69,78],"more":[70],"than":[71],"90%":[72],"accuracy,":[74],"orientations":[77],"standard":[79],"deviations":[80],"within":[81],"30":[82],"degrees,":[83],"situations":[85],"excluding":[86],"cases":[88],"where":[89],"all":[90],"are":[92],"opposite":[95],"direction":[96],"to":[97],"speaker's":[99],"orientation.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}