{"id":"https://openalex.org/W3202060924","doi":"https://doi.org/10.1145/3480139","title":"Efficient acoustic perception for virtual AI agents","display_name":"Efficient acoustic perception for virtual AI agents","publication_year":2021,"publication_date":"2021-09-22","ids":{"openalex":"https://openalex.org/W3202060924","doi":"https://doi.org/10.1145/3480139","mag":"3202060924"},"language":"en","primary_location":{"id":"doi:10.1145/3480139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3480139","pdf_url":null,"source":{"id":"https://openalex.org/S4210220973","display_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","issn_l":"2577-6193","issn":["2577-6193"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","raw_type":"journal-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/A5084655274","display_name":"Mike Chemistruck","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mike Chemistruck","raw_affiliation_strings":["Microsoft Mixed Reality, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Mixed Reality, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026198048","display_name":"Andrew S. Allen","orcid":"https://orcid.org/0000-0002-7232-2143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Allen","raw_affiliation_strings":["Microsoft Mixed Reality, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Mixed Reality, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105689838","display_name":"John Snyder","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Snyder","raw_affiliation_strings":["Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057559622","display_name":"Nikunj Raghuvanshi","orcid":"https://orcid.org/0000-0002-9154-5625"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikunj Raghuvanshi","raw_affiliation_strings":["Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084655274"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45084517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":"3","first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.7539752721786499},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6904797554016113},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.5959112644195557},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4986295700073242},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4878566265106201},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.479423463344574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.458659827709198},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.44637948274612427},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42568427324295044},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36825329065322876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3633466064929962},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3604881763458252},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.36024945974349976},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09515976905822754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539752721786499},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6904797554016113},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.5959112644195557},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4986295700073242},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4878566265106201},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.479423463344574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.458659827709198},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.44637948274612427},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42568427324295044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36825329065322876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3633466064929962},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3604881763458252},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.36024945974349976},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09515976905822754},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3480139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3480139","pdf_url":null,"source":{"id":"https://openalex.org/S4210220973","display_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","issn_l":"2577-6193","issn":["2577-6193"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1549940068","https://openalex.org/W1559975096","https://openalex.org/W1991139021","https://openalex.org/W2010311314","https://openalex.org/W2013358309","https://openalex.org/W2015833722","https://openalex.org/W2025127228","https://openalex.org/W2082565464","https://openalex.org/W2128301448","https://openalex.org/W2134773428","https://openalex.org/W2511428026","https://openalex.org/W2810259310","https://openalex.org/W2810882517","https://openalex.org/W2902105599","https://openalex.org/W2980247070","https://openalex.org/W3081890472","https://openalex.org/W3108332675","https://openalex.org/W4233097404","https://openalex.org/W4233385860"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2378076731","https://openalex.org/W2067046791","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2909888262","https://openalex.org/W2088988140","https://openalex.org/W2056769785","https://openalex.org/W2803103875","https://openalex.org/W2103019253"],"abstract_inverted_index":{"We":[0,44,61],"model":[1,50],"acoustic":[2],"perception":[3,41],"in":[4,55,88],"AI":[5],"agents":[6,92],"efficiently":[7],"within":[8],"complex":[9],"scenes":[10],"with":[11],"many":[12],"sound":[13,27,71,99],"events.":[14],"The":[15],"key":[16],"idea":[17],"is":[18,79,111],"to":[19,33,42],"employ":[20],"perceptual":[21],"parameters":[22],"that":[23,51,63],"capture":[24],"how":[25],"each":[26],"event":[28],"propagates":[29],"through":[30,94],"the":[31,34,56,69],"scene":[32],"agent's":[35],"location.":[36],"This":[37],"naturally":[38],"conforms":[39],"virtual":[40],"human.":[43],"propose":[45],"a":[46],"simplified":[47],"auditory":[48],"masking":[49],"limits":[52],"localization":[53,75],"capability":[54],"presence":[57],"of":[58],"distracting":[59],"sounds.":[60],"show":[62],"anisotropic":[64],"reflections":[65],"as":[66,68,73],"well":[67],"initial":[70],"serve":[72],"useful":[74],"cues.":[76],"Our":[77],"system":[78],"simple,":[80],"fast,":[81],"and":[82,84,96,101],"modular":[83],"obtains":[85],"natural":[86],"results":[87],"our":[89],"tests,":[90],"letting":[91],"navigate":[93],"passageways":[95],"portals":[97],"by":[98],"alone,":[100],"anticipate":[102],"or":[103],"track":[104],"occluded":[105],"but":[106],"audible":[107],"targets.":[108],"Source":[109],"code":[110],"provided.":[112]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}