{"id":"https://openalex.org/W4392903899","doi":"https://doi.org/10.1109/icassp48485.2024.10446749","title":"6DoF SELD: Sound Event Localization and Detection Using Microphones and Motion Tracking Sensors on Self-Motioning Human","display_name":"6DoF SELD: Sound Event Localization and Detection Using Microphones and Motion Tracking Sensors on Self-Motioning Human","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903899","doi":"https://doi.org/10.1109/icassp48485.2024.10446749"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021870144","display_name":"Akira Nakayama","orcid":"https://orcid.org/0000-0002-1084-494X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Nakayama","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017806490"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.9342,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94309158,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1411","last_page":"1415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.7215065956115723},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7104082107543945},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.5632824897766113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369133353233337},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5170395970344543},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5165414214134216},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.43879061937332153},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4143930971622467},{"id":"https://openalex.org/keywords/match-moving","display_name":"Match moving","score":0.4136682152748108},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09939754009246826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215065956115723},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7104082107543945},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.5632824897766113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369133353233337},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5170395970344543},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5165414214134216},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.43879061937332153},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4143930971622467},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.4136682152748108},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09939754009246826},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/icassp48485.2024.10446749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1982264772","https://openalex.org/W2028184103","https://openalex.org/W2072604753","https://openalex.org/W2074048320","https://openalex.org/W2109606373","https://openalex.org/W2752782242","https://openalex.org/W2810934215","https://openalex.org/W2883787264","https://openalex.org/W2937396132","https://openalex.org/W2982382207","https://openalex.org/W2991451943","https://openalex.org/W3035570025","https://openalex.org/W3083274258","https://openalex.org/W3108655859","https://openalex.org/W3117314925","https://openalex.org/W3206329344","https://openalex.org/W3213455868","https://openalex.org/W4221167652","https://openalex.org/W4239396298","https://openalex.org/W4287120192","https://openalex.org/W4295169404","https://openalex.org/W4312920378","https://openalex.org/W4376867606","https://openalex.org/W4380994299","https://openalex.org/W6631190155","https://openalex.org/W6743647910","https://openalex.org/W6779923105","https://openalex.org/W6796679619","https://openalex.org/W6798133626","https://openalex.org/W6853532597"],"related_works":["https://openalex.org/W3196329781","https://openalex.org/W4207023496","https://openalex.org/W585325435","https://openalex.org/W4317826877","https://openalex.org/W2648057","https://openalex.org/W2032880931","https://openalex.org/W4281846896","https://openalex.org/W2740961807","https://openalex.org/W1673651863","https://openalex.org/W4322774593"],"abstract_inverted_index":{"We":[0],"aim":[1],"to":[2,70,72,134,169],"perform":[3],"sound":[4,78],"event":[5],"localization":[6],"and":[7,39,124],"detection":[8],"(SELD)":[9],"using":[10,60],"wearable":[11,50,102],"equipment":[12],"for":[13,49,101,142],"a":[14,19,58,64,116,167],"moving":[15],"human,":[16],"such":[17],"as":[18],"pedestrian.":[20],"Conventional":[21],"SELD":[22,88,96,106,118,143,164],"tasks":[23],"have":[24],"dealt":[25],"only":[26,56],"with":[27,36,57,81,166],"microphone":[28,51,61],"arrays":[29,62],"located":[30],"in":[31,63,84],"static":[32],"positions.":[33],"However,":[34],"self-motion":[35,110,150],"three":[37,40],"rotational":[38],"translational":[41],"degrees":[42],"of":[43,77,87,111,147],"freedom":[44],"(6DoF)":[45],"shall":[46],"be":[47,68],"considered":[48],"arrays.":[52],"A":[53],"system":[54,119,137],"trained":[55],"dataset":[59,107,156],"fixed":[65],"position":[66],"would":[67],"unable":[69],"adapt":[71],"the":[73,85,104,109,136,145,148,159],"fast":[74],"relative":[75],"motion":[76,125],"events":[79],"associated":[80],"self-motion,":[82],"resulting":[83],"degradation":[86],"performance.":[89],"To":[90],"address":[91],"this,":[92],"we":[93,114],"designed":[94],"6DoF":[95],"Dataset":[97],"<sup":[98],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[100],"systems,":[103],"first":[105],"considering":[108],"microphones.":[112],"Furthermore,":[113],"proposed":[115,160],"multi-modal":[117],"that":[120,158],"jointly":[121],"utilizes":[122],"audio":[123],"tracking":[126],"sensor":[127,130,175],"signals.":[128,176],"These":[129],"signals":[131],"are":[132],"expected":[133],"help":[135],"find":[138],"useful":[139],"acoustic":[140,171],"cues":[141],"on":[144,154],"basis":[146],"current":[149],"state.":[151],"Experimental":[152],"results":[153],"our":[155],"show":[157],"method":[161],"effectively":[162],"improves":[163],"performance":[165],"mechanism":[168],"extract":[170],"features":[172],"conditioned":[173],"by":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-18T06:27:02.140700","created_date":"2025-10-10T00:00:00"}
