{"id":"https://openalex.org/W3161865163","doi":"https://doi.org/10.1145/3411764.3445687","title":"ProxiMic: Convenient Voice Activation via Close-to-Mic Speech Detected by a Single Microphone","display_name":"ProxiMic: Convenient Voice Activation via Close-to-Mic Speech Detected by a Single Microphone","publication_year":2021,"publication_date":"2021-05-06","ids":{"openalex":"https://openalex.org/W3161865163","doi":"https://doi.org/10.1145/3411764.3445687","mag":"3161865163"},"language":"en","primary_location":{"id":"doi:10.1145/3411764.3445687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411764.3445687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","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/A5018795899","display_name":"Yue Qin","orcid":"https://orcid.org/0000-0003-1351-5284"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Qin","raw_affiliation_strings":["Department of Computer Science and Technology Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043272273","display_name":"Chun Yu","orcid":"https://orcid.org/0000-0003-2591-7993"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yu","raw_affiliation_strings":["Department of Computer science and Technology Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer science and Technology Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010168076","display_name":"Zhaoheng Li","orcid":"https://orcid.org/0009-0002-0003-5062"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoheng Li","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016365745","display_name":"Mingyuan Zhong","orcid":"https://orcid.org/0000-0003-3184-759X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyuan Zhong","raw_affiliation_strings":["Paul G. Allen School of Computer Science &amp; Engineering University of Washington, United States"],"affiliations":[{"raw_affiliation_string":"Paul G. Allen School of Computer Science &amp; Engineering University of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055104105","display_name":"Yukang Yan","orcid":"https://orcid.org/0000-0001-7515-3755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukang Yan","raw_affiliation_strings":["Department of Computer Science and Technology Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057896400","display_name":"Yuanchun Shi","orcid":"https://orcid.org/0000-0003-2273-6927"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchun Shi","raw_affiliation_strings":["Department of Computer science and Technology Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer science and Technology Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018795899"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.7425,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9086545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/microphone","display_name":"Microphone","score":0.8548187017440796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7161323428153992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.627076268196106},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5660325884819031},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5657594203948975},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5639263391494751},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4151621162891388},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31308311223983765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22791892290115356},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1326618492603302},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10901939868927002}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8548187017440796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7161323428153992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.627076268196106},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5660325884819031},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5657594203948975},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5639263391494751},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4151621162891388},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31308311223983765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22791892290115356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1326618492603302},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10901939868927002},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3411764.3445687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411764.3445687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W59675154","https://openalex.org/W222641635","https://openalex.org/W821549425","https://openalex.org/W1533561824","https://openalex.org/W1849277567","https://openalex.org/W1971920230","https://openalex.org/W2004513044","https://openalex.org/W2046317813","https://openalex.org/W2051626970","https://openalex.org/W2060108923","https://openalex.org/W2076676508","https://openalex.org/W2093010905","https://openalex.org/W2099287431","https://openalex.org/W2113638573","https://openalex.org/W2115717467","https://openalex.org/W2127617367","https://openalex.org/W2128131274","https://openalex.org/W2129120544","https://openalex.org/W2157289187","https://openalex.org/W2157363431","https://openalex.org/W2251606987","https://openalex.org/W2394855416","https://openalex.org/W2397584766","https://openalex.org/W2402156731","https://openalex.org/W2477060772","https://openalex.org/W2526050071","https://openalex.org/W2565622304","https://openalex.org/W2603276336","https://openalex.org/W2652238127","https://openalex.org/W2787712888","https://openalex.org/W2787752687","https://openalex.org/W2793257307","https://openalex.org/W2889511491","https://openalex.org/W2890313351","https://openalex.org/W2896622783","https://openalex.org/W2897318954","https://openalex.org/W2941048526","https://openalex.org/W2949117887","https://openalex.org/W2949738301","https://openalex.org/W2973223332","https://openalex.org/W2980880049","https://openalex.org/W2983800141","https://openalex.org/W2985588979","https://openalex.org/W3003850239","https://openalex.org/W3029292602","https://openalex.org/W3029640333","https://openalex.org/W3083703874","https://openalex.org/W3163625767"],"related_works":["https://openalex.org/W2122030153","https://openalex.org/W2078842457","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2162449135","https://openalex.org/W2248536413","https://openalex.org/W2383417046","https://openalex.org/W4386336391","https://openalex.org/W3217417050","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Wake-up-free":[0],"techniques":[1],"(e.g.,":[2],"Raise-to-Speak)":[3],"are":[4],"important":[5],"for":[6],"improving":[7],"the":[8,37,43,57,71,125],"voice":[9],"input":[10,74],"experience.":[11],"We":[12],"present":[13],"ProxiMic,":[14,28],"a":[15,29,32,64,79,87],"close-to-mic":[16,53,92],"(within":[17],"5":[18],"cm)":[19],"speech":[20],"sensing":[21],"technique":[22],"using":[23],"only":[24],"one":[25],"microphone.":[26,72],"With":[27],"user":[30,65,128],"keeps":[31],"microphone-embedded":[33],"device":[34,44],"close":[35],"to":[36,42],"mouth":[38],"and":[39,67,136],"speaks":[40,66],"directly":[41],"without":[45],"wake-up":[46],"phrases":[47],"or":[48],"button":[49],"presses.":[50],"To":[51],"detect":[52],"speech,":[54],"we":[55],"use":[56],"feature":[58],"from":[59],"pop":[60,95],"noise":[61],"observed":[62],"when":[63],"blows":[68],"air":[69],"onto":[70],"Sound":[73],"is":[75,133],"first":[76],"passed":[77],"through":[78],"low-pass":[80],"adaptive":[81],"threshold":[82],"filter,":[83],"then":[84],"analyzed":[85],"by":[86],"CNN":[88],"which":[89,118],"detects":[90],"subtle":[91],"features":[93],"(mainly":[94],"noise).":[96],"Our":[97],"two-stage":[98],"algorithm":[99],"can":[100,119],"achieve":[101],"94.1%":[102],"activation":[103],"recall,":[104],"12.3":[105],"False":[106],"Accepts":[107],"per":[108,110],"Week":[109],"User":[111],"(FAWU)":[112],"with":[113],"68":[114],"KB":[115],"memory":[116],"size,":[117],"run":[120],"at":[121],"352":[122],"fps":[123],"on":[124],"smartphone.":[126],"The":[127],"study":[129],"shows":[130],"that":[131],"ProxiMic":[132],"efficient,":[134],"user-friendly,":[135],"practical.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
