{"id":"https://openalex.org/W4413640137","doi":"https://doi.org/10.1109/access.2025.3602885","title":"A Feasibility Study With In-the-Wild Data in Human Interaction Settings: Acoustic-Visual Fusion for Predictive Sound Source Positioning","display_name":"A Feasibility Study With In-the-Wild Data in Human Interaction Settings: Acoustic-Visual Fusion for Predictive Sound Source Positioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413640137","doi":"https://doi.org/10.1109/access.2025.3602885"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3602885","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3602885","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3602885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025153228","display_name":"Zhichao Chen","orcid":"https://orcid.org/0000-0002-1362-7940"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhichao Chen","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1362-7940","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100568646","display_name":"Chenfei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenfei Xu","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0009-0008-9778-7853","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077692984","display_name":"Huthaifa Ahmad","orcid":"https://orcid.org/0000-0002-8865-955X"},"institutions":[{"id":"https://openalex.org/I4210139080","display_name":"Eiken Chemical (Japan)","ror":"https://ror.org/04ff4e804","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210139080"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huthaifa Ahmad","raw_affiliation_strings":["RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan","institution_ids":["https://openalex.org/I4210139080"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021267164","display_name":"Yuya Okadome","orcid":"https://orcid.org/0009-0008-2961-8417"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Okadome","raw_affiliation_strings":["Department of Information and Computer Technology, Tokyo University of Science, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0008-2961-8417","affiliations":[{"raw_affiliation_string":"Department of Information and Computer Technology, Tokyo University of Science, Tokyo, Japan","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0805-7648","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011580159","display_name":"Yutaka Nakamura","orcid":"https://orcid.org/0000-0001-6307-5104"},"institutions":[{"id":"https://openalex.org/I4210139080","display_name":"Eiken Chemical (Japan)","ror":"https://ror.org/04ff4e804","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210139080"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaka Nakamura","raw_affiliation_strings":["RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6307-5104","affiliations":[{"raw_affiliation_string":"RIKEN Information Research and Development and Strategy Headquarters, RIKEN, Kyoto, Japan","institution_ids":["https://openalex.org/I4210139080"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025153228"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29010517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"150365","last_page":"150378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11692","display_name":"Noise Effects and Management","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11692","display_name":"Noise Effects and Management","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.92330002784729,"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/T10860","display_name":"Speech and Audio Processing","score":0.9143999814987183,"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/computer-science","display_name":"Computer science","score":0.6594631671905518},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.572027862071991},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5627819895744324},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.45710524916648865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45358115434646606},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32459282875061035},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32013535499572754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6594631671905518},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.572027862071991},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5627819895744324},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.45710524916648865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45358115434646606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32459282875061035},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32013535499572754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3602885","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3602885","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:34e51aeee05546f79a9cb9b146b7c679","is_oa":true,"landing_page_url":"https://doaj.org/article/34e51aeee05546f79a9cb9b146b7c679","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 150365-150378 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3602885","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3602885","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G3770326524","display_name":null,"funder_award_id":"Grant JPMJMS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"},{"id":"https://openalex.org/G7723672654","display_name":null,"funder_award_id":"JPMJMS2011","funder_id":"https://openalex.org/F4320311405","funder_display_name":"Japan Agency for Medical Research and Development"}],"funders":[{"id":"https://openalex.org/F4320311405","display_name":"Japan Agency for Medical Research and Development","ror":"https://ror.org/004rtk039"},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W1965172447","https://openalex.org/W1968438204","https://openalex.org/W2054852564","https://openalex.org/W2060108923","https://openalex.org/W2066218102","https://openalex.org/W2078976049","https://openalex.org/W2100893637","https://openalex.org/W2111460811","https://openalex.org/W2137666850","https://openalex.org/W2221409856","https://openalex.org/W2519091744","https://openalex.org/W2523338037","https://openalex.org/W2807015669","https://openalex.org/W2890952074","https://openalex.org/W3044495139","https://openalex.org/W3119221111","https://openalex.org/W3135282443","https://openalex.org/W3138340468","https://openalex.org/W4239441102","https://openalex.org/W4297841817","https://openalex.org/W4321435292","https://openalex.org/W4365800577","https://openalex.org/W4382939835","https://openalex.org/W4386065626","https://openalex.org/W4388820630","https://openalex.org/W4393032599","https://openalex.org/W4398249536"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Acoustic":[0],"data":[1,42,82],"inherently":[2],"contains":[3],"spatial":[4,38,69],"information":[5],"regarding":[6],"sounds.":[7],"Most":[8],"robotic":[9],"systems":[10],"rely":[11],"primarily":[12],"on":[13,112],"speech":[14],"recognition":[15],"results":[16],"for":[17,119],"control;":[18],"however,":[19],"the":[20,102,129],"utilization":[21],"of":[22,104],"rich":[23],"directional":[24],"cues":[25,70],"could":[26],"enhance":[27],"their":[28],"functionality.":[29],"Especially":[30],"in":[31,40,54,131,137],"human-robot":[32],"interaction,":[33],"both":[34],"verbal":[35],"content":[36],"and":[37,87],"context":[39],"acoustic":[41,52,90,105],"are":[43],"crucial.":[44],"To":[45],"capture":[46,108],"such":[47,121],"auditory":[48,68],"context,":[49],"we":[50,79,100,115],"employ":[51],"maps":[53,58,106],"this":[55],"research.":[56],"These":[57],"represent":[59],"soundscapes":[60],"as":[61,122],"2D":[62],"projections,":[63],"allowing":[64],"robots":[65],"to":[66,107,126],"integrate":[67],"with":[71,128],"visual":[72],"perception.":[73],"Using":[74],"a":[75,94],"custom":[76],"acoustic-visual":[77],"module,":[78],"collect":[80],"egocentric":[81],"from":[83],"four":[84],"daily":[85],"scenarios":[86],"generate":[88],"corresponding":[89],"maps.":[91],"By":[92],"demonstrating":[93],"predictive":[95],"sound":[96],"source":[97],"positioning":[98],"task,":[99],"confirm":[101],"potential":[103,117],"dialogue-relevant":[109],"information.":[110],"Based":[111],"these":[113],"findings,":[114],"anticipate":[116],"applications":[118],"robots,":[120],"identifying":[123],"individuals":[124],"attempting":[125],"engage":[127],"robot":[130],"crowded":[132],"environments":[133],"or":[134],"predicting":[135],"turn-taking":[136],"multi-party":[138],"conversations.":[139]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
