{"id":"https://openalex.org/W2141481925","doi":"https://doi.org/10.1109/icme.2003.1221247","title":"Using computer vision to generate customized spatial audio","display_name":"Using computer vision to generate customized spatial audio","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2141481925","doi":"https://doi.org/10.1109/icme.2003.1221247","mag":"2141481925"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5068295568","display_name":"Anand Mohan","orcid":"https://orcid.org/0009-0000-6118-6476"},"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":"A. Mohan","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"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":"R. Duraiswami","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, 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/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":"D.N. Zotkin","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038953612","display_name":"Daniel DeMenthon","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":"D. DeMenthon","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111878160","display_name":"L.S. Davis","orcid":"https://orcid.org/0009-0001-1414-8415"},"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":"L.S. Davis","raw_affiliation_strings":["Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Perceptual Interfaces and Reality Laboratory, UMIACS, University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Perceptual Interfaces & Reality Lab., Maryland Univ., College Park, MD, USA","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I2802964274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068295568"],"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":10,"citation_normalized_percentile":{"value":0.23242887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"III","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9883000254631042,"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":0.7719558477401733},{"id":"https://openalex.org/keywords/torso","display_name":"Torso","score":0.7575429677963257},{"id":"https://openalex.org/keywords/headphones","display_name":"Headphones","score":0.7290338277816772},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6684479713439941},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5908105373382568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44718822836875916},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43784016370773315},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3104707896709442},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.30635154247283936},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1330549418926239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719558477401733},{"id":"https://openalex.org/C523889960","wikidata":"https://www.wikidata.org/wiki/Q160695","display_name":"Torso","level":2,"score":0.7575429677963257},{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.7290338277816772},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6684479713439941},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5908105373382568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44718822836875916},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43784016370773315},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3104707896709442},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30635154247283936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1330549418926239},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2003.1221247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.1561","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.1561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.umiacs.umd.edu/~dz/pbpslist/icme2003_s9_z_final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1479894303","https://openalex.org/W1522342234","https://openalex.org/W1989742860","https://openalex.org/W2007217383","https://openalex.org/W2028673460","https://openalex.org/W2056522351","https://openalex.org/W2088115584","https://openalex.org/W2101298784","https://openalex.org/W2106792145","https://openalex.org/W2108668360","https://openalex.org/W2117678320","https://openalex.org/W2127086531","https://openalex.org/W2133001582","https://openalex.org/W2137383239","https://openalex.org/W2241211221","https://openalex.org/W6631180356","https://openalex.org/W7006436791"],"related_works":["https://openalex.org/W1568629288","https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2157165686","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926"],"abstract_inverted_index":{"Creating":[0],"high":[1,128],"quality":[2],"virtual":[3,183],"spatial":[4],"audio":[5],"over":[6],"headphones":[7],"requires":[8],"real-time":[9],"head":[10,34,151,174],"tracking,":[11],"personalized":[12,37],"head-related":[13],"transfer":[14],"functions":[15],"(HRTFs)":[16],"and":[17,39,51,73,77,87,100,164],"customized":[18],"room":[19,40,75],"response":[20],"models.":[21],"While":[22],"there":[23],"are":[24,43,104],"expensive":[25],"solutions":[26],"to":[27,65,78,172],"address":[28],"these":[29,42],"issues":[30],"based":[31,93],"on":[32,55],"costly":[33],"trackers,":[35],"measured":[36,133],"HRTFs":[38,143],"responses,":[41],"not":[44],"suitable":[45],"for":[46,69,106],"widespread":[47],"or":[48],"easy":[49],"deployment":[50],"use.":[52],"We":[53],"report":[54],"the":[56,71,74,97,101,159],"development":[57],"of":[58,96,142,158],"a":[59,115,140],"system":[60,82,179],"that":[61],"uses":[62,83],"computer":[63],"vision":[64],"produce":[66],"customizable":[67],"models":[68],"both":[70],"HRTF":[72,107,111],"response,":[76],"achieve":[79],"head-tracking.":[80],"The":[81,178],"relatively":[84],"inexpensive":[85],"cameras":[86],"widely":[88],"available":[89],"personal":[90],"computers.":[91],"Computer-vision":[92],"anthropometric":[94],"measurements":[95],"head,":[98],"torso,":[99],"external":[102],"ears":[103],"used":[105],"customization.":[108],"For":[109,127,150],"low-frequency":[110],"customization":[112,130],"we":[113,131,153],"employ":[114,132,154],"simple":[116],"head-and-torso":[117],"model":[118],"developed":[119],"recently":[120],"[V.":[121],"R.":[122],"Algazi":[123],"et":[124,147],"al.,":[125,148],"2002].":[126,149],"frequency":[129],"pinna":[134],"characteristics":[135],"as":[136],"an":[137,155,181],"index":[138],"into":[139],"database":[141],"[D.":[144,162],"N.":[145],"Zotkin":[146],"tracking":[152],"online":[156],"implementation":[157],"POSIT":[160],"algorithm":[161],"DeMenthon":[163],"L.":[165],"Davis,":[166],"1995]":[167],"along":[168],"with":[169],"active":[170],"markers":[171],"compute":[173],"pose":[175],"in":[176],"real-time.":[177],"provides":[180],"enhanced":[182],"listening":[184],"experience":[185],"at":[186],"low":[187],"cost.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
