{"id":"https://openalex.org/W2064034843","doi":"https://doi.org/10.1163/016918609x12529300552105","title":"Target Speech Detection and Separation for Communication with Humanoid Robots in Noisy Home Environments","display_name":"Target Speech Detection and Separation for Communication with Humanoid Robots in Noisy Home Environments","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2064034843","doi":"https://doi.org/10.1163/016918609x12529300552105","mag":"2064034843"},"language":"en","primary_location":{"id":"doi:10.1163/016918609x12529300552105","is_oa":false,"landing_page_url":"https://doi.org/10.1163/016918609x12529300552105","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-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/A5111821094","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":["a    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan;, Email: hyundon@kuis.kyoto-u.ac.jp","Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan;, Email: hyundon@kuis.kyoto-u.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"a    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan;, Email: hyundon@kuis.kyoto-u.ac.jp","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan;, Email: hyundon@kuis.kyoto-u.ac.jp","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676202","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0002-1587-0389"},"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"]},{"id":"https://openalex.org/I58716616","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883","country_code":"KR","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["b    The Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul 136-650, South Korea","The Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul 136-650, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"b    The Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul 136-650, South Korea","institution_ids":["https://openalex.org/I58716616","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"The Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul 136-650, South Korea","institution_ids":["https://openalex.org/I58716616"]}]},{"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":["c    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"c    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, 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":["d    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"d    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, 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":["e    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"e    Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3572,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56123733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"15","first_page":"2093","last_page":"2111"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/speech-recognition","display_name":"Speech recognition","score":0.7075027823448181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6720860600471497},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6294600963592529},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6203110218048096},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5579737424850464},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5486907362937927},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5222724080085754},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4683140218257904},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43539905548095703},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4330222010612488},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43109622597694397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42722100019454956},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4146798849105835},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.368624746799469},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2874366044998169}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7075027823448181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720860600471497},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6294600963592529},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6203110218048096},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5579737424850464},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5486907362937927},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5222724080085754},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4683140218257904},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43539905548095703},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4330222010612488},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43109622597694397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42722100019454956},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4146798849105835},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.368624746799469},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2874366044998169},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1163/016918609x12529300552105","is_oa":false,"landing_page_url":"https://doi.org/10.1163/016918609x12529300552105","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W653761051","https://openalex.org/W1869758581","https://openalex.org/W1932412845","https://openalex.org/W1974695940","https://openalex.org/W1985456342","https://openalex.org/W2046513212","https://openalex.org/W2100820878","https://openalex.org/W2102832314","https://openalex.org/W2110992439","https://openalex.org/W2131981197","https://openalex.org/W2146442351","https://openalex.org/W2147673046","https://openalex.org/W4249052411"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W4252682934","https://openalex.org/W2851491717","https://openalex.org/W2135485548","https://openalex.org/W2072884270","https://openalex.org/W2356426224","https://openalex.org/W2373767407"],"abstract_inverted_index":{"People":[0],"usually":[1],"talk":[2],"face":[3,5],"to":[4],"when":[6],"they":[7],"communicate":[8],"with":[9,133,155],"their":[10],"partner.":[11],"Therefore,":[12],"in":[13,51,111,119,122],"robot":[14,38,56],"audition,":[15],"the":[16,19,48,71,98,106,147,173],"recognition":[17,179],"of":[18,60,64,101,176],"front":[20,49],"talker":[21],"is":[22],"critical":[23],"for":[24,35,180],"smooth":[25],"interactions.":[26],"This":[27,85],"paper":[28],"presents":[29],"an":[30],"enhanced":[31,162],"speech":[32,44,92,134,165,178],"detection":[33,67],"method":[34,77],"a":[36,61,79,123,151],"humanoid":[37,152],"that":[39,94,142,159],"can":[40,90,131],"separate":[41],"and":[42,78,139,172],"recognize":[43],"signals":[45,93,166],"originating":[46],"from":[47,137,146],"even":[50,121],"noisy":[52,124],"home":[53],"environments.":[54],"The":[55,108],"audition":[57],"system":[58,109,161],"consists":[59],"new":[62],"type":[63],"voice":[65],"activity":[66],"(VAD)":[68],"based":[69,87],"on":[70,88,105],"complex":[72],"spectrum":[73],"circle":[74],"centroid":[75],"(CSCC)":[76],"maximum":[80],"signal-to-noise":[81],"ratio":[82],"(SNR)":[83,171],"beamformer.":[84],"VAD":[86],"CSCC":[89],"classify":[91],"are":[95],"retrieved":[96],"at":[97],"frontal":[99],"region":[100],"two":[102,156],"microphones":[103,157],"embedded":[104],"robot.":[107],"works":[110],"real-time":[112],"without":[113],"needing":[114],"training":[115],"filter":[116],"coefficients":[117],"given":[118],"advance":[120],"environment":[125],"(SNR":[126],">":[127],"0":[128],"dB).":[129],"It":[130],"cope":[132],"noise":[135],"generated":[136],"televisions":[138],"audio":[140],"devices":[141],"does":[143],"not":[144],"originate":[145],"center.":[148],"Experiments":[149],"using":[150],"robot,":[153],"SIG2,":[154],"showed":[158],"our":[160],"extracted":[163],"target":[164],"more":[167],"than":[168],"12":[169],"dB":[170],"success":[174],"rate":[175],"automatic":[177],"Japanese":[181],"words":[182],"was":[183],"increased":[184],"by":[185],"about":[186],"17":[187],"points.":[188]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
