{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T03:58:27Z","timestamp":1793505507819,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T00:00:00Z","timestamp":1620259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,5,6]]},"DOI":"10.1145\/3411764.3445687","type":"proceedings-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T01:28:50Z","timestamp":1620437330000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["ProxiMic: Convenient Voice Activation via Close-to-Mic Speech Detected by a Single Microphone"],"prefix":"10.1145","author":[{"given":"Yue","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer science and Technology Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoheng","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyuan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Paul G. Allen School of Computer Science & Engineering University of Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukang","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanchun","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer science and Technology Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,5,7]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Apple. 2020. Use Siri on all your Apple devices - Apple Support. Website. https:\/\/support.apple.com\/en-us\/HT204389#apple-watch."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.003"},{"key":"e_1_3_2_2_3_1","volume-title":"The technology of binaural listening","author":"Argentieri S","unstructured":"S Argentieri, A Portello, M Bernard, P Danes, and B Gas. 2013. Binaural systems in robotics. In The technology of binaural listening. Springer-Verlag, Berlin, Germany, 225\u2013253."},{"key":"e_1_3_2_2_4_1","unstructured":"Baidu. 2020. Baidu ASR. http:\/\/ai.baidu.com\/tech\/speech\/asr."},{"key":"e_1_3_2_2_5_1","volume-title":"Brain\u2013computer interfaces for speech communication. Speech communication 52, 4","author":"Brumberg S","year":"2010","unstructured":"Jonathan\u00a0S Brumberg, Alfonso Nieto-Castanon, Philip\u00a0R Kennedy, and Frank\u00a0H Guenther. 2010. Brain\u2013computer interfaces for speech communication. Speech communication 52, 4 (2010), 367\u2013379."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.985676"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-296"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2014.986642"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.026"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242603"},{"key":"e_1_3_2_2_11_1","first-page":"1","article-title":"EchoWhisper: Exploring an Acoustic-based Silent Speech Interface for Smartphone Users","volume":"4","author":"Gao Yang","year":"2020","unstructured":"Yang Gao, Yincheng Jin, Jiyang Li, Seokmin Choi, and Zhanpeng Jin. 2020. EchoWhisper: Exploring an Acoustic-based Silent Speech Interface for Smartphone Users. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 3 (2020), 1\u201327.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952659"},{"key":"e_1_3_2_2_13_1","volume-title":"Aki Harma, and John Mourjopoulos.","author":"Georganti Eleftheria","year":"2011","unstructured":"Eleftheria Georganti, Tobias May, Steven van\u00a0de Par, Aki Harma, and John Mourjopoulos. 2011. Speaker distance detection using a single microphone. IEEE transactions on audio, speech, and language processing 19, 7(2011), 1949\u20131961."},{"key":"e_1_3_2_2_14_1","volume-title":"Steven Van De\u00a0Par, and John Mourjopoulos","author":"Georganti Eleftheria","year":"2013","unstructured":"Eleftheria Georganti, Tobias May, Steven Van De\u00a0Par, and John Mourjopoulos. 2013. Sound source distance estimation in rooms based on statistical properties of binaural signals. IEEE transactions on audio, speech, and language processing 21, 8(2013), 1727\u20131741."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a037)","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Proceedings of the 32nd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a037), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 448\u2013456. http:\/\/proceedings.mlr.press\/v37\/ioffe15.html"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172977"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"e_1_3_2_2_20_1","volume-title":"New Report: Over 1 Billion Devices Provide Voice Assistant Access Today and Highest Usage is on Smartphones. Website.","author":"BRET","year":"2018","unstructured":"BRET KINSELLA. 2018. New Report: Over 1 Billion Devices Provide Voice Assistant Access Today and Highest Usage is on Smartphones. Website."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268943"},{"key":"e_1_3_2_2_23_1","volume-title":"International Conference on Applied Human Factors and Ergonomics. Springer-Verlag","author":"L\u00f3pez Gustavo","year":"2017","unstructured":"Gustavo L\u00f3pez, Luis Quesada, and Luis\u00a0A Guerrero. 2017. Alexa vs. Siri vs. Cortana vs. Google Assistant: a comparison of speech-based natural user interfaces. In International Conference on Applied Human Factors and Ergonomics. Springer-Verlag, Cham, Switzerland, 241\u2013250."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/765891.765971"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376147"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359278"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4647"},{"key":"e_1_3_2_2_28_1","volume-title":"2010 18th European Signal Processing Conference. IEEE","author":"Mesaros Annamaria","year":"2010","unstructured":"Annamaria Mesaros, Toni Heittola, Antti Eronen, and Tuomas Virtanen. 2010. Acoustic event detection in real life recordings. In 2010 18th European Signal Processing Conference. IEEE, Piscataway, NJ, USA, 1267\u20131271."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/2618265"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174214"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-011-0470-5"},{"key":"e_1_3_2_2_32_1","volume-title":"Efficient voice activity detection algorithms using long-term speech information. Speech communication 42, 3-4","author":"Ram\u0131rez Javier","year":"2004","unstructured":"Javier Ram\u0131rez, Jos\u00e9\u00a0C Segura, Carmen Ben\u0131tez, Angel De\u00a0La\u00a0Torre, and Antonio Rubio. 2004. Efficient voice activity detection algorithms using long-term speech information. Speech communication 42, 3-4 (2004), 271\u2013287."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3239092.3265968"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/29.32276"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-92"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-37"},{"key":"e_1_3_2_2_38_1","unstructured":"ShotSpotter. 2020. ShotSpotter. https:\/\/www.shotspotter.com\/."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2204"},{"key":"e_1_3_2_2_40_1","volume-title":"2nd International Conference on Learning Representations, Workshop Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). ICLR","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In 2nd International Conference on Learning Representations, Workshop Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). ICLR 2014, Banff, Canada, 1\u20138. http:\/\/arxiv.org\/abs\/1312.6034"},{"key":"e_1_3_2_2_41_1","volume-title":"A statistical model-based voice activity detection","author":"Sohn Jongseo","year":"1999","unstructured":"Jongseo Sohn, Nam\u00a0Soo Kim, and Wonyong Sung. 1999. A statistical model-based voice activity detection. IEEE signal processing letters 6, 1 (1999), 1\u20133."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.848229"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2006.08.004"},{"key":"e_1_3_2_2_45_1","volume-title":"Beamforming: A versatile approach to spatial filtering","author":"Van\u00a0Veen D","year":"1988","unstructured":"Barry\u00a0D Van\u00a0Veen and Kevin\u00a0M Buckley. 1988. Beamforming: A versatile approach to spatial filtering. IEEE assp magazine 5, 2 (1988), 4\u201324."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445484"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347950"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376810"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369808"},{"key":"e_1_3_2_2_50_1","volume-title":"2014 22nd European Signal Processing Conference (EUSIPCO). IEEE","author":"Zehetner Andreas","year":"2014","unstructured":"Andreas Zehetner, Martin Hagm\u00fcller, and Franz Pernkopf. 2014. Wake-up-word spotting for mobile systems. In 2014 22nd European Signal Processing Conference (EUSIPCO). IEEE, Piscataway, NJ, USA, 1472\u20131476."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330761"}],"event":{"name":"CHI '21: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '21","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3411764.3445687","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3411764.3445687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:14:34Z","timestamp":1790000074000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3411764.3445687"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,6]]},"references-count":52,"alternative-id":["10.1145\/3411764.3445687","10.1145\/3411764"],"URL":"https:\/\/doi.org\/10.1145\/3411764.3445687","relation":{},"subject":[],"published":{"date-parts":[[2021,5,6]]},"assertion":[{"value":"2021-05-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}