{"id":"https://openalex.org/W2146442351","doi":"https://doi.org/10.1109/robot.2008.4543745","title":"Two-channel-based voice activity detection for humanoid robots in noisy home environments","display_name":"Two-channel-based voice activity detection for humanoid robots in noisy home environments","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W2146442351","doi":"https://doi.org/10.1109/robot.2008.4543745","mag":"2146442351"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2008.4543745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2008.4543745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Robotics and Automation","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/A5054240780","display_name":"Hyun-Don Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hyun-Don Kim","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Speech Media Process. Group, Kyoto Univ., Kyoto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Speech Media Process. Group, Kyoto Univ., Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Speech Media Process. Group, Kyoto Univ., Kyoto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Speech Media Process. Group, Kyoto Univ., Kyoto","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7605,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74343434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"49","issue":null,"first_page":"3495","last_page":"3501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.7737089395523071},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6403602361679077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.630246102809906},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5318892598152161},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5313385725021362},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5257202982902527},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4994034767150879},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4615910053253174},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4443853497505188},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4398159682750702},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43701714277267456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4307108223438263},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4143553674221039},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.4120280146598816},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40506213903427124},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3156552314758301},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17592430114746094},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08868670463562012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737089395523071},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6403602361679077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.630246102809906},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5318892598152161},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5313385725021362},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5257202982902527},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4994034767150879},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4615910053253174},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4443853497505188},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4398159682750702},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43701714277267456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4307108223438263},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4143553674221039},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.4120280146598816},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40506213903427124},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3156552314758301},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17592430114746094},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08868670463562012},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robot.2008.4543745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2008.4543745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.6090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.6090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/~okuno/paper/ICRA08-Kim.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1487212816","https://openalex.org/W1869758581","https://openalex.org/W1912147533","https://openalex.org/W1974695940","https://openalex.org/W1985456342","https://openalex.org/W1985690171","https://openalex.org/W2081817329","https://openalex.org/W2100820878","https://openalex.org/W2101329857","https://openalex.org/W2102832314","https://openalex.org/W2110992439","https://openalex.org/W2113638573","https://openalex.org/W2131981197","https://openalex.org/W2147673046","https://openalex.org/W2267719592","https://openalex.org/W2538750502","https://openalex.org/W3103998211","https://openalex.org/W4285719527","https://openalex.org/W6639229959","https://openalex.org/W6639939913","https://openalex.org/W6693364154"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2072884270","https://openalex.org/W2002243964","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W4386474880","https://openalex.org/W2022538999"],"abstract_inverted_index":{"The":[0],"purpose":[1],"of":[2,64,72,77,126],"this":[3],"research":[4],"is":[5],"to":[6,26,31,154,158],"accurately":[7],"classify":[8,54],"the":[9,14,45,55,62,69,120,124,127],"speech":[10,28,56,107],"signals":[11,57,74,79],"originating":[12],"from":[13],"front":[15,63],"even":[16,95],"in":[17,87,96],"noisy":[18,97],"home":[19],"environments.":[20],"This":[21,150],"ability":[22],"can":[23,53,85,104],"help":[24],"robots":[25],"improve":[27],"recognition":[29],"and":[30,103,116,145],"spot":[32],"keywords.":[33],"We":[34],"therefore":[35],"developed":[36,132],"a":[37,133,156],"new":[38],"voice":[39],"activity":[40],"detection":[41],"(VAD)":[42],"based":[43],"on":[44],"complex":[46],"spectrum":[47,141],"circle":[48],"centroid":[49],"(CSCC)":[50],"method.":[51],"It":[52],"that":[58,76],"are":[59],"received":[60],"at":[61],"two":[65,165],"microphones":[66],"by":[67,81,110],"comparing":[68],"spectral":[70],"energy":[71],"observed":[73],"with":[75,106,139,160],"target":[78],"estimated":[80],"CSCC.":[82],"Also,":[83],"it":[84],"work":[86],"real":[88],"time":[89],"without":[90],"training":[91],"filter":[92],"coefficients":[93],"beforehand":[94],"environments":[98],"(SNR":[99],"\u226b":[100],"0":[101],"dB)":[102],"cope":[105,159],"noises":[108],"generated":[109],"audio-visual":[111],"equipments":[112],"such":[113],"as":[114],"televisions":[115],"audio":[117],"devices.":[118],"Since":[119],"CSCC":[121],"method":[122],"requires":[123],"directions":[125],"noise":[128],"signals,":[129],"we":[130],"also":[131],"sound":[134,162],"source":[135],"localization":[136],"system":[137,151],"integrated":[138],"cross-power":[140],"phase":[142],"(CSP)":[143],"analysis":[144],"an":[146],"expectation-maximization":[147],"(EM)":[148],"algorithm.":[149],"was":[152],"demonstrated":[153],"enable":[155],"robot":[157],"multiple":[161],"sources":[163],"using":[164],"microphones.":[166]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
