{"id":"https://openalex.org/W2122663001","doi":"https://doi.org/10.1109/icme.2002.1035570","title":"An evaluation of sound source identification with RWCP sound scene database in real acoustic environments","display_name":"An evaluation of sound source identification with RWCP sound scene database in real acoustic environments","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2122663001","doi":"https://doi.org/10.1109/icme.2002.1035570","mag":"2122663001"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2002.1035570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","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/A5009257831","display_name":"Takanobu Nishiura","orcid":"https://orcid.org/0000-0002-1706-4743"},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Nishiura","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","Faculty of Systems Engineering, Wakayama University, Wakayama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Faculty of Systems Engineering, Wakayama University, Wakayama, Japan","institution_ids":["https://openalex.org/I75198481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080776631","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0003-3492-7093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Nakamura","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9073,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86484801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"265","last_page":"268"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.7923916578292847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7411324381828308},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.628942608833313},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5729773640632629},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5694825649261475},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5644215941429138},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5579066872596741},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4700673520565033},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4566286504268646},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.44450733065605164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29451805353164673},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.16708216071128845},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07725712656974792}],"concepts":[{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.7923916578292847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411324381828308},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.628942608833313},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5729773640632629},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5694825649261475},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5644215941429138},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5579066872596741},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4700673520565033},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4566286504268646},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.44450733065605164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29451805353164673},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.16708216071128845},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07725712656974792},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2002.1035570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W58138822","https://openalex.org/W1912147533","https://openalex.org/W2105613081","https://openalex.org/W2130432819","https://openalex.org/W2155276444","https://openalex.org/W2165869870","https://openalex.org/W2245569228","https://openalex.org/W4247773827","https://openalex.org/W6602370547"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2098651198","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668","https://openalex.org/W1515932869"],"abstract_inverted_index":{"It":[0],"is":[1,19,85,101],"very":[2],"important":[3],"for":[4,23,86,102],"a":[5,74,143],"hands-free":[6],"speech":[7,12,131],"interface":[8],"to":[9],"capture":[10],"distant":[11],"with":[13,69,129,158],"high":[14],"quality.":[15],"A":[16],"microphone":[17,144],"array":[18,145],"an":[20],"ideal":[21],"candidate":[22],"this":[24,27],"purpose.":[25],"However,":[26],"approach":[28],"requires":[29],"localizing":[30,47,57],"the":[31,48,58,118,152,155,159],"target":[32,59],"talker.":[33],"Conventional":[34],"talker":[35,60,76,112,147],"localization":[36,77,90],"methods":[37],"in":[38,164],"multiple":[39,49,63,87,108,126],"sound":[40,50,64,88,103,109,121,127,134,161],"source":[41,65,89,104,122],"environments":[42,167],"not":[43],"only":[44],"have":[45,55],"difficulty":[46,56],"sources":[51,110,128],"accurately,":[52],"but":[53],"also":[54],"among":[61,106,124],"known":[62],"positions.":[66],"To":[67],"cope":[68],"these":[70],"problems,":[71],"we":[72],"propose":[73],"new":[75],"method":[78],"consisting":[79],"of":[80,154],"two":[81],"algorithms.":[82],"One":[83],"algorithm":[84,100],"based":[91,136],"on":[92,117,137],"CSP":[93],"(cross-power":[94],"spectrum":[95],"phase)":[96],"analysis.":[97],"The":[98],"other":[99],"identification":[105,123],"localized":[107,125],"towards":[111,146],"localization.":[113,148],"We":[114,149],"particularly":[115],"focus":[116],"latter":[119],"statistical":[120,130],"and":[132,142],"environmental":[133],"models":[135],"GMMs":[138],"(Gaussian":[139],"mixture":[140],"models)":[141],"especially":[150],"evaluate":[151],"performance":[153],"proposed":[156],"algorithms":[157],"RWCP":[160],"scene":[162],"database":[163],"real":[165],"acoustic":[166],"(RWCP-DB).":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}