{"id":"https://openalex.org/W2054052343","doi":"https://doi.org/10.1109/icassp.2010.5496123","title":"Head orientation estimation of a speaker by utilizing kurtosis of a DOA histogram with restoration of distance effect","display_name":"Head orientation estimation of a speaker by utilizing kurtosis of a DOA histogram with restoration of distance effect","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2054052343","doi":"https://doi.org/10.1109/icassp.2010.5496123","mag":"2054052343"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5496123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5496123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["Central Research Laboratory, Hitachi and Limited, Kokubunji, Tokyo, Japan","Central Research Laboratory, Hitachi, Ltd., 1-280 Higashi-Koigakubo, Kokubunji-shi, Tokyo 185-8601, Japan"],"affiliations":[{"raw_affiliation_string":"Central Research Laboratory, Hitachi and Limited, Kokubunji, Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Central Research Laboratory, Hitachi, Ltd., 1-280 Higashi-Koigakubo, Kokubunji-shi, Tokyo 185-8601, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052394367","display_name":"Yohei Kawaguchi","orcid":"https://orcid.org/0000-0002-2329-5441"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Kawaguchi","raw_affiliation_strings":["Central Research Laboratory, Hitachi and Limited, Kokubunji, Tokyo, Japan","Central Research Laboratory, Hitachi, Ltd., 1-280 Higashi-Koigakubo, Kokubunji-shi, Tokyo 185-8601, Japan"],"affiliations":[{"raw_affiliation_string":"Central Research Laboratory, Hitachi and Limited, Kokubunji, Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Central Research Laboratory, Hitachi, Ltd., 1-280 Higashi-Koigakubo, Kokubunji-shi, Tokyo 185-8601, Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021883714"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":1.6857,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8406173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"136"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/kurtosis","display_name":"Kurtosis","score":0.9504919648170471},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.7753208875656128},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.7505095601081848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6325849890708923},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5861573815345764},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.551618754863739},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5374648571014404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302868485450745},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46441859006881714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44099700450897217},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4107639193534851},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25171810388565063},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09301501512527466},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08669871091842651},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07298296689987183},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06485098600387573}],"concepts":[{"id":"https://openalex.org/C166963901","wikidata":"https://www.wikidata.org/wiki/Q287251","display_name":"Kurtosis","level":2,"score":0.9504919648170471},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.7753208875656128},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.7505095601081848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6325849890708923},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5861573815345764},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.551618754863739},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5374648571014404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302868485450745},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46441859006881714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44099700450897217},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4107639193534851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25171810388565063},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09301501512527466},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08669871091842651},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07298296689987183},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06485098600387573},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5496123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5496123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W168089823","https://openalex.org/W207220130","https://openalex.org/W1506558619","https://openalex.org/W1555217905","https://openalex.org/W2073652545","https://openalex.org/W2098651198","https://openalex.org/W2102790159","https://openalex.org/W2147494647","https://openalex.org/W6608301978","https://openalex.org/W6630289078"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2041060376","https://openalex.org/W3119734852","https://openalex.org/W2011776247"],"abstract_inverted_index":{"In":[0,61],"this":[1,42],"paper,":[2],"we":[3],"propose":[4],"a":[5,15,36,85,90,127,145,159,164],"head-orientation":[6,166],"estimation":[7,27,64,167],"method":[8,28,40,54,71,152],"from":[9,138],"multichannel":[10],"acoustic":[11],"signals.":[12],"Sharpness":[13],"of":[14,35,49,65,74,78,87,89,126,158],"DOA":[16,26,76,91],"histogram":[17,77,92],"which":[18,135],"is":[19,82,116,129,136],"extracted":[20],"by":[21,119,131],"using":[22],"the":[23,32,46,50,66,69,75,94,102,105,108,120,132,139,150,155],"sparseness":[24],"based":[25],"varies":[29],"depending":[30],"on":[31,101,144],"head":[33,47,124,156],"orientation":[34,48,125,157],"speaker.":[37,51],"The":[38,52,113,123],"proposed":[39,53,70,95,151],"utilizes":[41],"phenomenon":[43],"to":[44,63],"estimate":[45,154],"uses":[55],"more":[56,161],"than":[57,163],"two":[58],"microphone":[59,109],"arrays.":[60],"addition":[62],"speaker":[67,106,128,160],"location,":[68],"estimates":[72],"kurtosis":[73,98,134],"each":[79],"array.":[80],"Kurtosis":[81],"regarded":[83],"as":[84],"measure":[86],"sharpness":[88],"in":[93],"method.":[96,168],"However,":[97],"also":[99],"depends":[100],"distance":[103,114,140],"between":[104],"and":[107],"array":[110],"(distance":[111],"effect).":[112],"effect":[115],"experimentally":[117],"revealed":[118],"regression":[121],"analysis.":[122],"estimated":[130],"restored":[133],"free":[137],"effect.":[141],"Experimental":[142],"results":[143],"reverberant":[146],"environment":[147],"show":[148],"that":[149],"can":[153],"accurately":[162],"conventional":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}