{"id":"https://openalex.org/W7125925083","doi":"https://doi.org/10.1109/smc58881.2025.11343015","title":"Visual-based spatial audio generation system for multi-speaker environments <sup>*</sup>","display_name":"Visual-based spatial audio generation system for multi-speaker environments <sup>*</sup>","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125925083","doi":"https://doi.org/10.1109/smc58881.2025.11343015"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124090443","display_name":"Xiaojing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaojing Liu","raw_affiliation_strings":["Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116249268","display_name":"Ogulcan Gurelli","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ogulcan Gurelli","raw_affiliation_strings":["Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124143371","display_name":"Yan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Xidian University,Department of Electrical Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,Department of Electrical Engineering,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":null,"display_name":"Joshua Reiss","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua Reiss","raw_affiliation_strings":["Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of Electronic Engineering and Computer Science, Center for Digital Music (C4DM),United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.611559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5827","last_page":"5832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7021999955177307,"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":0.7021999955177307,"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/T11448","display_name":"Face recognition and analysis","score":0.10400000214576721,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06279999762773514,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/binaural-recording","display_name":"Binaural recording","score":0.7032999992370605},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.46720001101493835},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4124000072479248},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.37040001153945923},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36739999055862427},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.36010000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759000062942505},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7032999992370605},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4124000072479248},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.36010000109672546},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5625683069229126,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2137324511","https://openalex.org/W2146673011","https://openalex.org/W2159591770","https://openalex.org/W2516001803","https://openalex.org/W2746574320","https://openalex.org/W2800288142","https://openalex.org/W2897067191","https://openalex.org/W2898527280","https://openalex.org/W2923206072","https://openalex.org/W2952218014","https://openalex.org/W2963037989","https://openalex.org/W2963566548","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2982624843","https://openalex.org/W3003293188","https://openalex.org/W3157866890","https://openalex.org/W3174854700","https://openalex.org/W4390638513","https://openalex.org/W4393405428","https://openalex.org/W4402727359"],"related_works":[],"abstract_inverted_index":{"In":[0],"multimedia":[1,155],"applications":[2],"such":[3],"as":[4],"films":[5],"and":[6,35,79,119,124],"video":[7],"games,":[8],"spatial":[9,47,60,80,115],"audio":[10,25,44,61,81,118],"techniques":[11],"are":[12],"widely":[13],"employed":[14],"to":[15,142],"enhance":[16],"user":[17],"experiences":[18],"by":[19],"simulating":[20],"3D":[21],"sound:":[22],"transforming":[23],"mono":[24],"into":[26],"binaural":[27,90],"formats.":[28],"However,":[29],"this":[30],"process":[31],"is":[32,96],"often":[33],"complex":[34],"labor-intensive":[36],"for":[37,73,152],"sound":[38,140],"designers,":[39],"requiring":[40,88],"precise":[41],"synchronization":[42],"of":[43,49],"with":[45],"the":[46,84,132,136],"positions":[48],"visual":[50],"components.":[51],"To":[52],"address":[53],"these":[54],"challenges,":[55],"we":[56],"propose":[57],"a":[58,149],"visual-based":[59],"generation":[62,102],"system":[63,67,85,95,103,138],"-":[64],"an":[65],"automated":[66],"that":[68,110],"integrates":[69],"face":[70],"detection":[71],"YOLOv8":[72],"object":[74],"detection,":[75],"monocular":[76],"depth":[77],"estimation,":[78],"techniques.":[82],"Notably,":[83],"operates":[86],"without":[87],"additional":[89],"dataset":[91],"training.":[92],"The":[93],"proposed":[94,137],"evaluated":[97],"against":[98],"existing":[99],"Spatial":[100],"Audio":[101],"using":[104],"objective":[105],"metrics.":[106],"Experimental":[107],"results":[108,145],"demonstrate":[109],"our":[111],"method":[112],"significantly":[113],"improves":[114],"consistency":[116],"between":[117],"video,":[120],"enhances":[121],"speech":[122],"quality,":[123],"performs":[125],"robustly":[126],"in":[127,154],"multi-speaker":[128],"scenarios.":[129],"By":[130],"streamlining":[131],"audio-visual":[133],"alignment":[134],"process,":[135],"enables":[139],"engineers":[141],"achieve":[143],"high-quality":[144],"efficiently,":[146],"making":[147],"it":[148],"valuable":[150],"tool":[151],"professionals":[153],"production.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}