{"id":"https://openalex.org/W7123491322","doi":"https://doi.org/10.1109/mmsp64401.2025.11324337","title":"White-box Differentiable Model of Perceived Localisation","display_name":"White-box Differentiable Model of Perceived Localisation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123491322","doi":"https://doi.org/10.1109/mmsp64401.2025.11324337"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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/A5082266557","display_name":"Antoine Souchaud","orcid":"https://orcid.org/0000-0003-0753-9060"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Antoine Souchaud","raw_affiliation_strings":["University of Surrey,Institute of Sound Recording,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Institute of Sound Recording,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077562489","display_name":"Pedro Llad\u00f3","orcid":"https://orcid.org/0000-0001-9095-0912"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pedro Llad\u00f3","raw_affiliation_strings":["University of Surrey,Institute of Sound Recording,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Institute of Sound Recording,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069437201","display_name":"Annika Neidhardt","orcid":"https://orcid.org/0000-0002-4243-5737"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Annika Neidhardt","raw_affiliation_strings":["University of Surrey,Institute of Sound Recording,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Institute of Sound Recording,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovi\u0107","raw_affiliation_strings":["King’s College London,Department of Engineering,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering,London,United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080242003","display_name":"Enzo De Sena","orcid":"https://orcid.org/0000-0002-8007-4370"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Enzo De Sena","raw_affiliation_strings":["University of Surrey,Institute of Sound Recording,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Institute of Sound Recording,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082266557"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68250945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9246000051498413,"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"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9246000051498413,"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/T10860","display_name":"Speech and Audio Processing","score":0.02800000086426735,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.01860000006854534,"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/rendering","display_name":"Rendering (computer graphics)","score":0.751800000667572},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6966999769210815},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5575000047683716},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4749000072479248},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.44209998846054077},{"id":"https://openalex.org/keywords/auditory-display","display_name":"Auditory display","score":0.4334000051021576},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.42100000381469727},{"id":"https://openalex.org/keywords/auditory-perception","display_name":"Auditory perception","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.751800000667572},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5835000276565552},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.44209998846054077},{"id":"https://openalex.org/C171179263","wikidata":"https://www.wikidata.org/wiki/Q4820026","display_name":"Auditory display","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.4072999954223633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.2872999906539917},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28369998931884766},{"id":"https://openalex.org/C100142294","wikidata":"https://www.wikidata.org/wiki/Q2070426","display_name":"Selective auditory attention","level":4,"score":0.2800999879837036},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.48746001720428467,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W222641635","https://openalex.org/W1965159237","https://openalex.org/W2015636737","https://openalex.org/W2029432770","https://openalex.org/W2065691163","https://openalex.org/W2166682639","https://openalex.org/W2416573875","https://openalex.org/W2729516000","https://openalex.org/W2976852561","https://openalex.org/W3007201150","https://openalex.org/W3021865613","https://openalex.org/W4226064907","https://openalex.org/W4233385860","https://openalex.org/W4285194056","https://openalex.org/W4285413288","https://openalex.org/W4319596413","https://openalex.org/W4392901771","https://openalex.org/W4394596108","https://openalex.org/W4405017986","https://openalex.org/W4416251219"],"related_works":[],"abstract_inverted_index":{"Auditory":[0],"models":[1,16,149],"are":[2,58,94],"useful":[3],"tools":[4],"for":[5],"estimating":[6],"perceptual":[7,45],"attributes":[8],"of":[9,20,76,100,117,139,150],"a":[10,25,122],"sound":[11,22,125,144],"field.":[12],"Integrating":[13],"such":[14],"auditory":[15,77,151],"in":[17,50,107,121],"the":[18,34,44,89,98,101,137],"optimisation":[19,52,116],"immersive":[21,143],"systems":[23,145],"is":[24,31,40],"promising":[26],"strategy":[27],"when":[28],"listeners\u2019":[29],"perception":[30],"central":[32],"to":[33,42,47],"application.":[35],"To":[36],"that":[37,88,93],"end,":[38],"differentiability":[39],"key":[41],"allowing":[43],"model":[46,75,90,103,113],"be":[48],"included":[49],"gradient-based":[51],"loops.":[53],"Existing":[54],"differentiable":[55,74,148],"models,":[56],"however,":[57],"black-box":[59],"deep-learning":[60],"based,":[61],"which":[62],"limits":[63],"their":[64],"interpretability.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"an":[71,81],"analytical":[72],"white-box":[73,147],"localisation":[78],"based":[79],"on":[80],"existing":[82],"non-differential":[83,102],"model.":[84],"Our":[85],"evaluations":[86],"show":[87],"produces":[91],"outputs":[92,99],"highly":[95],"correlated":[96],"with":[97],"and":[104,141],"data":[105],"collected":[106],"subjective":[108],"listening":[109],"tests.":[110],"The":[111],"proposed":[112],"also":[114],"enables":[115],"amplitude":[118],"panning":[119],"laws":[120],"stereophonic":[123],"spatial":[124],"field":[126],"rendering":[127],"through":[128],"gradient":[129],"descent.":[130],"This":[131],"study":[132],"therefore":[133],"demonstrates,":[134],"more":[135],"generally,":[136],"feasibility":[138],"designing":[140],"optimising":[142],"using":[146],"perception.":[152]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-01-14T00:00:00"}