{"id":"https://openalex.org/W3093949709","doi":"https://doi.org/10.1145/3379337.3415588","title":"Direction-of-Voice (DoV) Estimation for Intuitive Speech Interaction with Smart Devices Ecosystems","display_name":"Direction-of-Voice (DoV) Estimation for Intuitive Speech Interaction with Smart Devices Ecosystems","publication_year":2020,"publication_date":"2020-10-16","ids":{"openalex":"https://openalex.org/W3093949709","doi":"https://doi.org/10.1145/3379337.3415588","mag":"3093949709"},"language":"en","primary_location":{"id":"doi:10.1145/3379337.3415588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3379337.3415588","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3379337.3415588","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3379337.3415588","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010929285","display_name":"Karan Ahuja","orcid":"https://orcid.org/0000-0003-2497-0530"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karan Ahuja","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026188811","display_name":"Andy Kong","orcid":"https://orcid.org/0000-0002-4529-0000"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andy Kong","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030011411","display_name":"Mayank Goel","orcid":"https://orcid.org/0000-0003-1237-7545"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Goel","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029290807","display_name":"Chris Harrison","orcid":"https://orcid.org/0000-0001-5312-3619"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Harrison","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010929285"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.8937,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91897375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1121","last_page":"1131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8335325717926025},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6518861055374146},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.628134548664093},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5915923714637756},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.5723986029624939},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5393180251121521},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48050034046173096},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4701146185398102},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3756275177001953},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09570816159248352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335325717926025},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6518861055374146},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.628134548664093},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5915923714637756},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.5723986029624939},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5393180251121521},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48050034046173096},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4701146185398102},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3756275177001953},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09570816159248352},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3379337.3415588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3379337.3415588","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3379337.3415588","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3379337.3415588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3379337.3415588","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3379337.3415588","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093949709.pdf","grobid_xml":"https://content.openalex.org/works/W3093949709.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W19651392","https://openalex.org/W168089823","https://openalex.org/W253649471","https://openalex.org/W274496805","https://openalex.org/W766042757","https://openalex.org/W860825873","https://openalex.org/W1585574785","https://openalex.org/W1966506333","https://openalex.org/W2011865252","https://openalex.org/W2024925870","https://openalex.org/W2046317813","https://openalex.org/W2074335765","https://openalex.org/W2081841744","https://openalex.org/W2096241474","https://openalex.org/W2100335648","https://openalex.org/W2107049458","https://openalex.org/W2114863372","https://openalex.org/W2129188305","https://openalex.org/W2132605602","https://openalex.org/W2135643110","https://openalex.org/W2147494647","https://openalex.org/W2151806889","https://openalex.org/W2166547995","https://openalex.org/W2167608257","https://openalex.org/W2169730407","https://openalex.org/W2401746695","https://openalex.org/W2402008087","https://openalex.org/W2464712732","https://openalex.org/W2525932165","https://openalex.org/W2594412520","https://openalex.org/W2611943505","https://openalex.org/W2625477228","https://openalex.org/W2781321626","https://openalex.org/W2787712888","https://openalex.org/W2890735031","https://openalex.org/W2972559661","https://openalex.org/W3009203799","https://openalex.org/W3029297226","https://openalex.org/W3104757150","https://openalex.org/W3124056356","https://openalex.org/W3149173221","https://openalex.org/W4285719527","https://openalex.org/W4301484901","https://openalex.org/W6622391697"],"related_works":["https://openalex.org/W2429057255","https://openalex.org/W2187546663","https://openalex.org/W148745890","https://openalex.org/W4389670110","https://openalex.org/W2611942503","https://openalex.org/W4315621326","https://openalex.org/W2899790217","https://openalex.org/W2598865957","https://openalex.org/W1576092969","https://openalex.org/W2524154428"],"abstract_inverted_index":{"Future":[0],"homes":[1],"and":[2,17,30,47,101,136,151,158,169,180],"offices":[3],"will":[4],"feature":[5],"increasingly":[6],"dense":[7],"ecosystems":[8],"of":[9,56,95,112,143,172],"IoT":[10],"devices,":[11],"such":[12],"as":[13,79],"smart":[14],"lighting,":[15],"speakers,":[16],"domestic":[18],"appliances.":[19],"Voice":[20,113],"input":[21],"is":[22],"a":[23,57,80,92,96,127,134],"natural":[24,135],"candidate":[25],"for":[26],"interacting":[27],"with":[28,121],"out-of-reach":[29],"often":[31],"small":[32],"devices":[33,124],"that":[34,155],"lack":[35],"full-sized":[36],"physical":[37],"interfaces.":[38],"However,":[39],"at":[40,131],"present,":[41],"voice":[42,119,175],"agents":[43],"generally":[44],"require":[45],"wake-words":[46],"device":[48],"names":[49],"in":[50,84,133],"order":[51],"to":[52,65],"specify":[53],"the":[54,86,110,141,170],"target":[55],"spoken":[58,103,149],"command":[59,128],"(e.g.,":[60],"'Hey":[61],"Alexa,":[62],"kitchen":[63],"lights":[64],"full":[66],"bright-ness').":[67],"In":[68],"this":[69],"research,":[70],"we":[71,105,162],"explore":[72],"whether":[73],"speech":[74],"alone":[75],"can":[76],"be":[77],"used":[78],"directional":[81],"communication":[82],"channel,":[83],"much":[85,177],"same":[87],"way":[88],"visual":[89],"gaze":[90],"specifies":[91],"focus.":[93],"Instead":[94],"device's":[97],"microphones":[98],"simply":[99],"receiving":[100],"processing":[102],"commands,":[104],"suggest":[106],"they":[107],"also":[108],"infer":[109],"Direction":[111],"(DoV).":[114],"Our":[115],"approach":[116,166],"innately":[117],"enables":[118],"commands":[120],"addressability":[122],"(i.e.,":[123],"know":[125],"if":[126],"was":[129],"directed":[130],"them)":[132],"rapid":[137],"manner.":[138],"We":[139],"quantify":[140],"accuracy":[142],"our":[144,164],"implementation":[145],"across":[146],"users,":[147],"rooms,":[148],"phrases,":[150],"other":[152],"key":[153],"factors":[154],"affect":[156],"performance":[157],"usability.":[159],"Taken":[160],"together,":[161],"believe":[163],"DoV":[165],"demonstrates":[167],"feasibility":[168],"promise":[171],"making":[173],"distributed":[174],"interactions":[176],"more":[178],"intuitive":[179],"fluid.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}
