{"id":"https://openalex.org/W3029297226","doi":"https://doi.org/10.1145/3313831.3376427","title":"Soundr: Head Position and Orientation Prediction Using a Microphone Array","display_name":"Soundr: Head Position and Orientation Prediction Using a Microphone Array","publication_year":2020,"publication_date":"2020-04-21","ids":{"openalex":"https://openalex.org/W3029297226","doi":"https://doi.org/10.1145/3313831.3376427","mag":"3029297226"},"language":"en","primary_location":{"id":"doi:10.1145/3313831.3376427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3313831.3376427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems","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/A5108052998","display_name":"Junrui Yang","orcid":"https://orcid.org/0000-0002-2064-5231"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jackie (Junrui) Yang","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102785192","display_name":"Gaurab Banerjee","orcid":"https://orcid.org/0000-0003-4858-7683"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurab Banerjee","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110212471","display_name":"Vishesh Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishesh Gupta","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002419188","display_name":"Monica S. Lam","orcid":"https://orcid.org/0000-0002-1205-1302"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monica S. Lam","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072285921","display_name":"James A. Landay","orcid":"https://orcid.org/0000-0003-1520-8894"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James A. Landay","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9909999966621399,"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/headset","display_name":"Headset","score":0.885068416595459},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.7790044546127319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737486958503723},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.658717691898346},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.5738505125045776},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5626991987228394},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5105627775192261},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45605725049972534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44948136806488037},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4494577646255493},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.402325838804245},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39388877153396606},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1038522720336914}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.885068416595459},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.7790044546127319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737486958503723},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.658717691898346},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.5738505125045776},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5626991987228394},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5105627775192261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45605725049972534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44948136806488037},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4494577646255493},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.402325838804245},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39388877153396606},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1038522720336914},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3313831.3376427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3313831.3376427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W168089823","https://openalex.org/W253649471","https://openalex.org/W1485619570","https://openalex.org/W1555217905","https://openalex.org/W1585574785","https://openalex.org/W1666923889","https://openalex.org/W1977909099","https://openalex.org/W1991032800","https://openalex.org/W1994630425","https://openalex.org/W2007465845","https://openalex.org/W2044541911","https://openalex.org/W2065854286","https://openalex.org/W2067192547","https://openalex.org/W2113638573","https://openalex.org/W2129821199","https://openalex.org/W2149057406","https://openalex.org/W2149264547","https://openalex.org/W2167608257","https://openalex.org/W2168185689","https://openalex.org/W2401746695","https://openalex.org/W2403444653","https://openalex.org/W2408708312","https://openalex.org/W2508429489","https://openalex.org/W2621068604","https://openalex.org/W2776323726","https://openalex.org/W2884822476","https://openalex.org/W2964121744","https://openalex.org/W2980743394","https://openalex.org/W3104947433"],"related_works":["https://openalex.org/W2549567669","https://openalex.org/W2323345712","https://openalex.org/W104838418","https://openalex.org/W1532889363","https://openalex.org/W4292416459","https://openalex.org/W2394331374","https://openalex.org/W4225253169","https://openalex.org/W2626842453","https://openalex.org/W2946426818","https://openalex.org/W4321180712"],"abstract_inverted_index":{"Although":[0],"state-of-the-art":[1],"smart":[2,43],"speakers":[3,44,106],"can":[4,63],"hear":[5],"a":[6,10,30,108],"user's":[7,48],"speech,":[8],"unlike":[9],"human":[11,105],"assistant":[12],"these":[13],"devices":[14],"cannot":[15],"figure":[16,64],"out":[17,65],"users'":[18],"verbal":[19],"references":[20,67],"based":[21,73],"on":[22,74],"their":[23,56],"head":[24,52,115],"location":[25,50],"and":[26,51,71,78,128,161],"orientation.":[27],"Soundr":[28,62],"presents":[29],"novel":[31],"interaction":[32],"technique":[33],"that":[34,59,98],"leverages":[35],"the":[36,47,75,100],"built-in":[37],"microphone":[38],"array":[39],"found":[40,154],"in":[41],"most":[42],"to":[45,68,112,142,158,163],"infer":[46],"spatial":[49],"orientation":[53,130],"using":[54],"only":[55],"voice.":[57],"With":[58],"extra":[60],"information,":[61],"users":[66],"objects,":[69],"people,":[70],"locations":[72],"speakers'":[76],"gaze,":[77],"also":[79],"provide":[80,84,114],"relative":[81],"directions.":[82],"To":[83],"training":[85],"data":[86,96],"for":[87,135,146],"our":[88],"neural":[89],"network,":[90],"we":[91],"collected":[92],"751":[93],"minutes":[94],"of":[95,99,126,133],"(50x":[97],"best":[101],"prior":[102],"work)":[103],"from":[104],"leveraging":[107],"virtual":[109],"reality":[110],"headset":[111],"accurately":[113],"tracking":[116],"ground":[117],"truth.":[118],"Our":[119],"results":[120],"achieve":[121],"an":[122,129],"average":[123],"positional":[124],"error":[125],"0.31m":[127],"angle":[131],"accuracy":[132],"34.3\u00b0":[134],"each":[136],"voice":[137],"command.":[138],"A":[139],"user":[140,144],"study":[141],"evaluate":[143],"preferences":[145],"controlling":[147],"IoT":[148],"appliances":[149],"by":[150],"talking":[151],"at":[152],"them":[153],"this":[155],"new":[156],"approach":[157],"be":[159],"fast":[160],"easy":[162],"use.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}