{"id":"https://openalex.org/W2029477306","doi":"https://doi.org/10.1109/wiamis.2013.6616137","title":"Robust localization and tracking of multiple speakers in real environments for binaural robot audition","display_name":"Robust localization and tracking of multiple speakers in real environments for binaural robot audition","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2029477306","doi":"https://doi.org/10.1109/wiamis.2013.6616137","mag":"2029477306"},"language":"en","primary_location":{"id":"doi:10.1109/wiamis.2013.6616137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","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/A5002024136","display_name":"Ui-Hyun 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":true,"raw_author_name":"Ui-Hyun Kim","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto, , Japan"],"affiliations":[{"raw_affiliation_string":"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, , 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, Kyoto, Japan","Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto, , Japan"],"affiliations":[{"raw_affiliation_string":"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, , Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002024136"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.3192,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56594823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9991999864578247,"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":0.9977999925613403,"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/binaural-recording","display_name":"Binaural recording","score":0.7961509227752686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7258025407791138},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7076383233070374},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.634247362613678},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5940976142883301},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5104562044143677},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4924233853816986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4762130677700043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.412400484085083}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7961509227752686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258025407791138},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7076383233070374},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.634247362613678},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5940976142883301},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5104562044143677},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4924233853816986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4762130677700043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.412400484085083},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/wiamis.2013.6616137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1581848821","https://openalex.org/W2046317813","https://openalex.org/W2086912078","https://openalex.org/W2129120544","https://openalex.org/W2146085064","https://openalex.org/W3144831910","https://openalex.org/W6681841294"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2129850190","https://openalex.org/W2026165661","https://openalex.org/W2099651033","https://openalex.org/W4256317079"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22,69],"multisource":[4,24,53],"sound":[5],"localization":[6],"method":[7,14,27,75],"based":[8],"on":[9,63],"the":[10,17,50,64],"generalized":[11],"cross-correlation":[12],"(GCC)":[13],"weighted":[15],"by":[16,56],"phase":[18],"transform":[19],"(PHAT)":[20],"and":[21,34],"novel":[23],"speech":[25,54],"tracking":[26,55,83],"consisting":[28],"of":[29,52],"voice":[30],"activity":[31],"detection":[32],"(VAD)":[33],"K-means":[35,44],"clustering":[36,45],"algorithm":[37,46],"for":[38,49],"binaural":[39],"robot":[40,67],"audition.":[41],"The":[42],"standard":[43],"was":[47],"improved":[48],"purpose":[51],"adding":[57],"two":[58],"additional":[59],"steps.":[60],"Experiments":[61],"conducted":[62],"SIG-2":[65],"humanoid":[66],"in":[68,80],"real":[70],"environment":[71],"show":[72],"that":[73],"our":[74],"can":[76],"track":[77],"multiple":[78],"speakers":[79],"real-time":[81],"with":[82],"error":[84],"below":[85],"4.35\u00b0.":[86]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
