{"id":"https://openalex.org/W4408345922","doi":"https://doi.org/10.1109/icassp49660.2025.10889134","title":"Efficient Spatial Audio Rendering Via Differentiable FIR To IIR Estimation","display_name":"Efficient Spatial Audio Rendering Via Differentiable FIR To IIR Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345922","doi":"https://doi.org/10.1109/icassp49660.2025.10889134"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5093925866","display_name":"Armin Gerami","orcid":null},"institutions":[{"id":"https://openalex.org/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Armin Gerami","raw_affiliation_strings":["University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051464607","display_name":"Bowen Zhi","orcid":null},"institutions":[{"id":"https://openalex.org/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Zhi","raw_affiliation_strings":["University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056837482","display_name":"Dmitry N. Zotkin","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]},{"id":"https://openalex.org/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry N. Zotkin","raw_affiliation_strings":["University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]},{"id":"https://openalex.org/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":["University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,Perceptual Interfaces & Reality Lab, Computer Science & UMIACS,College Park,USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093925866"],"corresponding_institution_ids":["https://openalex.org/I2802964274","https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04699932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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":0.988099992275238,"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":0.9366000294685364,"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":0.7997728586196899},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7037209272384644},{"id":"https://openalex.org/keywords/infinite-impulse-response","display_name":"Infinite impulse response","score":0.687150239944458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6828435659408569},{"id":"https://openalex.org/keywords/finite-impulse-response","display_name":"Finite impulse response","score":0.575484573841095},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3304517865180969},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2635694146156311},{"id":"https://openalex.org/keywords/digital-filter","display_name":"Digital filter","score":0.22367915511131287},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22267553210258484},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21006280183792114},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.08841797709465027}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7997728586196899},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7037209272384644},{"id":"https://openalex.org/C183816354","wikidata":"https://www.wikidata.org/wiki/Q665617","display_name":"Infinite impulse response","level":4,"score":0.687150239944458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6828435659408569},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.575484573841095},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3304517865180969},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2635694146156311},{"id":"https://openalex.org/C36390408","wikidata":"https://www.wikidata.org/wiki/Q1163067","display_name":"Digital filter","level":3,"score":0.22367915511131287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22267553210258484},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21006280183792114},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.08841797709465027},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1986562171","https://openalex.org/W2002271909","https://openalex.org/W2053927648","https://openalex.org/W2068325601","https://openalex.org/W2080101027","https://openalex.org/W2089473323","https://openalex.org/W2100991756","https://openalex.org/W2101298784","https://openalex.org/W2105601277","https://openalex.org/W2108668360","https://openalex.org/W2139448165","https://openalex.org/W2142265541","https://openalex.org/W2150590350","https://openalex.org/W2164521661","https://openalex.org/W2302108082","https://openalex.org/W2748917647","https://openalex.org/W2759873418","https://openalex.org/W3012167292","https://openalex.org/W3091983754","https://openalex.org/W3162467951","https://openalex.org/W3165004824","https://openalex.org/W3168515913","https://openalex.org/W3183773838","https://openalex.org/W3216715155","https://openalex.org/W4225300994","https://openalex.org/W4372341113","https://openalex.org/W4391454500","https://openalex.org/W4392910510","https://openalex.org/W6660251904","https://openalex.org/W6771763809","https://openalex.org/W6842676699"],"related_works":["https://openalex.org/W4312785053","https://openalex.org/W2142009384","https://openalex.org/W3140661709","https://openalex.org/W2021631062","https://openalex.org/W3138047207","https://openalex.org/W2129450128","https://openalex.org/W2810377961","https://openalex.org/W3007580271","https://openalex.org/W2072565115","https://openalex.org/W2031892245"],"abstract_inverted_index":{"The":[0],"MPEG-H":[1],"standard":[2,53],"for":[3,54,71,110,138,145,180],"spatial":[4,21,57,146],"audio":[5,22,58,147],"proposes":[6],"the":[7,43,47,51,83],"rendering":[8,148],"of":[9,25,42,46,67,112,149,166],"multiple":[10],"auditory":[11],"objects":[12],"(up":[13],"to":[14,18,81],"16)":[15],"and":[16,39,77,134,168,185],"ambisonics":[17],"create":[19],"a":[20,40,56,105,113,118,132,157,176,187],"scene.":[23,59],"Convolution":[24],"these":[26,101],"(and":[27],"their":[28],"early":[29],"environmental":[30],"reflections)":[31],"with":[32,92],"user-specific":[33],"Head":[34],"Related":[35],"Impulse":[36],"Responses":[37],"(HRIRs),":[38],"treatment":[41],"late":[44],"tail":[45],"room":[48],"reverberation,":[49],"is":[50,62,123],"gold":[52],"creating":[55],"However,":[60],"this":[61],"expensive":[63],"both":[64],"in":[65,164,175],"terms":[66,165],"computational":[68],"time/battery":[69],"power":[70],"finite":[72],"impulse":[73,95],"response":[74,96],"(FIR)":[75],"convolution,":[76],"device":[78],"memory":[79],"required":[80],"store":[82],"HRIRs.":[84],"If":[85],"quality":[86],"could":[87],"be":[88],"maintained,":[89],"an":[90,126],"implementation":[91,181],"equivalent":[93],"infinite":[94],"(IIR)":[97],"filters":[98],"would":[99],"mitigate":[100],"costs.":[102],"We":[103,141,152],"propose":[104],"novel":[106],"differentiable":[107,135],"optimization":[108],"approach":[109,174],"determination":[111],"IIR":[114],"filter":[115],"cascade":[116],"from":[117,192],"given":[119],"FIR":[120],"filter.":[121],"This":[122],"done":[124],"via":[125],"application":[127],"specific":[128],"formulation":[129],"that":[130],"yields":[131],"convex":[133],"cost":[136],"function":[137],"such":[139],"conversion.":[140],"describe":[142],"our":[143,154,173],"results":[144],"HRIR":[150,162],"convolution.":[151],"compare":[153],"work":[155],"against":[156],"recent":[158],"neural":[159],"network":[160],"based":[161],"estimation":[163],"accuracy":[167],"speed.":[169],"Finally,":[170],"we":[171],"implemented":[172],"real-time":[177],"setting,":[178],"suitable":[179],"on":[182],"DSP":[183],"hardware,":[184],"conducted":[186],"small":[188],"user":[189],"study.":[190],"Results":[191],"human":[193],"participants":[194],"were":[195],"positive.":[196]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}