{"id":"https://openalex.org/W4416402681","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00144","title":"AudioVisual Coherence in Action: How Spatial Audio Enhances Object Detection and Immersive Experience in VR Environments","display_name":"AudioVisual Coherence in Action: How Spatial Audio Enhances Object Detection and Immersive Experience in VR Environments","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4416402681","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00144"},"language":null,"primary_location":{"id":"doi:10.1109/ismar-adjunct68609.2025.00144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","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/A5101781790","display_name":"Di Zhang","orcid":"https://orcid.org/0000-0003-0237-2361"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhang Di","raw_affiliation_strings":["Communication University of China"],"affiliations":[{"raw_affiliation_string":"Communication University of China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120606109","display_name":"Peng Ziyu","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Ziyu","raw_affiliation_strings":["Communication University of China"],"affiliations":[{"raw_affiliation_string":"Communication University of China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600271","display_name":"Long Ye","orcid":"https://orcid.org/0000-0002-3562-5612"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Long","raw_affiliation_strings":["Communication University of China"],"affiliations":[{"raw_affiliation_string":"Communication University of China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101781790"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39197701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"684","last_page":"687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.6650999784469604,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.6650999784469604,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.25679999589920044,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.039400000125169754,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.6355999708175659},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.6003999710083008},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"Spatial coherence","score":0.5713000297546387},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5602999925613403},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5192000269889832},{"id":"https://openalex.org/keywords/headphones","display_name":"Headphones","score":0.42500001192092896},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.42170000076293945},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4032999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656999826431274},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6355999708175659},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.5713000297546387},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3255999982357025},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.325300008058548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismar-adjunct68609.2025.00144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","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":11,"referenced_works":["https://openalex.org/W124275677","https://openalex.org/W2898527280","https://openalex.org/W3008886302","https://openalex.org/W3037994420","https://openalex.org/W3162847139","https://openalex.org/W4302011018","https://openalex.org/W4308238200","https://openalex.org/W4313405549","https://openalex.org/W4394825436","https://openalex.org/W4405180401","https://openalex.org/W4406266227"],"related_works":[],"abstract_inverted_index":{"In":[0],"virtual":[1],"reality":[2],"(VR)":[3],"environments,":[4],"users":[5],"often":[6],"face":[7],"limitations":[8],"in":[9,35,136,161,178],"spatial":[10,29,32,45,67,85,92,113,131,138,145,159,180,192],"awareness":[11],"and":[12,40,69,78,121,163,182],"object":[13,57,118],"localization,":[14],"particularly":[15],"for":[16,105,171,186],"elements":[17],"outside":[18],"their":[19],"immediate":[20],"field":[21],"of":[22,43,157,175],"view.":[23],"This":[24],"study":[25],"investigates":[26],"how":[27],"audiovisual":[28,176],"coherence":[30,177],"affects":[31],"perception":[33,86,181],"efficacy":[34],"VR,":[36],"comparing":[37],"the":[38,172],"subjective":[39,153],"objective":[41],"impacts":[42],"different":[44],"audio":[46,93,100,114,132,146,160,193],"modalities.":[47],"We":[48],"conducted":[49],"a":[50,97],"controlled":[51],"experiment":[52],"with":[53,103,129],"24":[54],"participants":[55],"performing":[56],"detection":[58,119],"tasks":[59],"under":[60],"three":[61],"conditions:":[62],"5.1.4":[63,91,130,158],"surround":[64],"sound,":[65],"binaural":[66],"audio,":[68,128],"traditional":[70],"2D":[71,127],"audio.":[72],"Our":[73],"analysis":[74,142],"encompassed":[75],"omnidirectional,":[76],"rear-space,":[77],"overhead":[79],"target":[80],"scenarios":[81],"to":[82,126],"comprehensively":[83],"evaluate":[84],"performance.":[87],"To":[88],"enable":[89],"precise":[90],"implementation,":[94],"we":[95],"developed":[96],"custom":[98],"ASIO-based":[99],"system":[101],"integrated":[102],"Unity":[104],"accurate":[106],"multi-channel":[107],"rendering.":[108],"Results":[109],"demonstrate":[110],"that":[111,144],"both":[112],"systems":[115],"significantly":[116,147],"improved":[117,148],"accuracy":[120],"reduced":[122,164],"response":[123],"times":[124],"compared":[125],"showing":[133],"superior":[134],"performance":[135],"challenging":[137],"conditions.":[139],"Head":[140],"movement":[141],"revealed":[143],"user":[149],"attention":[150],"allocation,":[151],"while":[152],"evaluations":[154],"indicated":[155],"advantages":[156],"comfort":[162],"fatigue.":[165],"These":[166],"findings":[167],"provide":[168],"empirical":[169],"evidence":[170],"critical":[173],"role":[174],"VR":[179],"offer":[183],"practical":[184],"insights":[185],"optimizing":[187],"immersive":[188],"experiences":[189],"through":[190],"appropriate":[191],"implementation.":[194]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-18T00:00:00"}
