{"id":"https://openalex.org/W2133087131","doi":"https://doi.org/10.1109/iros.2008.4650977","title":"Target speech detection and separation for humanoid robots in sparse dialogue with noisy home environments","display_name":"Target speech detection and separation for humanoid robots in sparse dialogue with noisy home environments","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W2133087131","doi":"https://doi.org/10.1109/iros.2008.4650977","mag":"2133087131"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2008.4650977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2008.4650977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5040460745","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":["Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676201","display_name":"Jin-Sung Kim","orcid":"https://orcid.org/0000-0001-9839-4762"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea","Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul, Korea, Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea","institution_ids":["https://openalex.org/I58716616"]},{"raw_affiliation_string":"Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul, Korea, Republic","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":"K. Komatani","raw_affiliation_strings":["Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","[Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, 606-8501, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, 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":"T. Ogata","raw_affiliation_strings":["Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","[Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, 606-8501, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, 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":"H.G. Okuno","raw_affiliation_strings":["Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","[Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, 606-8501, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Speech Media Processing Group, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, 606-8501, Japan]","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1407,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.7961551,"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":"1705","last_page":"1711"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9984999895095825,"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/humanoid-robot","display_name":"Humanoid robot","score":0.7574982643127441},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7410420179367065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940038204193115},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6258099675178528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5207640528678894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44983112812042236},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34353870153427124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.200670063495636}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7574982643127441},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7410420179367065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940038204193115},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6258099675178528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5207640528678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44983112812042236},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34353870153427124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.200670063495636}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2008.4650977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2008.4650977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.7769","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.7769","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/IROS08-Kim-1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1869758581","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/W2129328412","https://openalex.org/W2131981197","https://openalex.org/W2147673046","https://openalex.org/W2159284737","https://openalex.org/W2538750502","https://openalex.org/W3103998211","https://openalex.org/W6639229959"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W2129850190","https://openalex.org/W4256317079","https://openalex.org/W2295425790","https://openalex.org/W4389009354","https://openalex.org/W1974803039","https://openalex.org/W1991876829","https://openalex.org/W2088677124","https://openalex.org/W1589423663","https://openalex.org/W1569471492"],"abstract_inverted_index":{"In":[0],"normal":[1],"human":[2],"communication,":[3],"people":[4],"face":[5],"the":[6,15,22,25,54,77,103,111,152,178],"speaker":[7],"when":[8],"listening":[9],"and":[10,48,84,144,177],"usually":[11],"pay":[12],"attention":[13],"to":[14],"speaker\u2019":[16],"face.":[17],"Therefore,":[18],"in":[19,57,116,124,127],"robot":[20,44,62],"audition,":[21],"recognition":[23,184],"of":[24,66,70,106,181],"front":[26,55],"talker":[27],"is":[28],"critical":[29],"for":[30,41,185],"smooth":[31],"interactions.":[32],"This":[33,90],"paper":[34],"presents":[35],"an":[36],"enhanced":[37,167],"speech":[38,50,97,139,170,183],"detection":[39,73],"method":[40,83],"a":[42,67,85,128,156],"humanoid":[43,157],"that":[45,99,147,164],"can":[46,95,136],"separate":[47],"recognize":[49],"signals":[51,98,171],"originating":[52],"from":[53,142,151],"even":[56,126],"noisy":[58,129],"home":[59],"environments.":[60],"The":[61,113],"audition":[63],"system":[64,114,166],"consists":[65],"new":[68],"type":[69],"voice":[71],"activity":[72],"(VAD)":[74],"based":[75,92],"on":[76,93,110],"complex":[78],"spectrum":[79],"circle":[80],"centroid":[81],"(CSCC)":[82],"maximum":[86],"signal-to-noise":[87],"(Max-SNR)":[88],"beamformer.":[89],"VAD":[91],"CSCC":[94],"classify":[96],"are":[100],"retrieved":[101],"at":[102],"frontal":[104],"region":[105],"two":[107,161],"microphones":[108,162],"embedded":[109],"robot.":[112],"works":[115],"real-time":[117],"without":[118],"needing":[119],"training":[120],"filter":[121],"coefficients":[122],"given":[123],"advance":[125],"environment":[130],"(SNR":[131],"\u226b":[132],"0":[133],"dB).":[134],"It":[135],"cope":[137],"with":[138,160],"noise":[140],"generated":[141],"televisions":[143],"audio":[145],"devices":[146],"does":[148],"not":[149],"originate":[150],"center.":[153],"Experiments":[154],"using":[155],"robot,":[158],"SIG2,":[159],"showed":[163],"our":[165],"extracted":[168],"target":[169],"more":[172],"than":[173],"12":[174],"dB":[175],"(SNR)":[176],"success":[179],"rate":[180],"automatic":[182],"Japanese":[186],"words":[187],"was":[188],"increased":[189],"about":[190],"17":[191],"points.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}