{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:27:24Z","timestamp":1780054044216,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T00:00:00Z","timestamp":1587427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["1900638"],"award-info":[{"award-number":["1900638"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,4,21]]},"DOI":"10.1145\/3313831.3376427","type":"proceedings-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T15:16:49Z","timestamp":1590592609000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Soundr: Head Position and Orientation Prediction Using a Microphone Array"],"prefix":"10.1145","author":[{"given":"Jackie (Junrui)","family":"Yang","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurab","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishesh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monica S.","family":"Lam","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James A.","family":"Landay","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,4,23]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2018. WebRTC Home | WebRTC. https:\/\/webrtc.org\/. (2018). (Accessed on 09\/19\/2019)."},{"key":"e_1_3_2_2_2_1","unstructured":"2019. Smart AR Home on the App Store. https:\/\/apps.apple.com\/us\/app\/smart-ar-home\/id1344696207. (2019). (Accessed on 09\/19\/2019)."},{"key":"e_1_3_2_2_3_1","unstructured":"2019. U.S. Smart Speaker Ownership Rises 40% in 2018 to 66.4 Million and Amazon Echo Maintains Market Share Lead Says New Report from Voicebot - Voicebot. https:\/\/voicebot.ai\/2019\/03\/07\/u-s-smart-speaker-own ership-rises-40-in-2018-to-66--4-million-and-amazo n-echo-maintains-market-share-lead-says-new-repor t-from-voicebot\/. (2019). (Accessed on 09\/18\/2019)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-257"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1996.0024"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-745"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/hscma.2008.4538690"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--662-04619--7_8"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2599174"},{"key":"e_1_3_2_2_10_1","unstructured":"Eiichi Ito. 2001. Multi-modal Interface with Voice and Head Tracking for Multiple Home Appliances. In INTERACT. 727--728."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/csnt.2015.189"},{"key":"e_1_3_2_2_12_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--540--30568--2_16"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/274497.274531"},{"key":"e_1_3_2_2_15_1","volume-title":"ITG Symposium. VDE, 1--5.","author":"M\u00fcller Menno","unstructured":"Menno M\u00fcller, Steven van de Par, and Joerg Bitzer. 2016. Head-Orientation-Based Device Selection: Are You Talking to Me?. In Speech Communication; 12. ITG Symposium. VDE, 1--5."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354285"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.3257548"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.31.309"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2014.2336636"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/258549.258821"},{"key":"e_1_3_2_2_21_1","volume-title":"2005 13th European Signal Processing Conference. IEEE, 1--4.","author":"Ronzhin Andrey","year":"2005","unstructured":"Andrey Ronzhin and Alexey Karpov. 2005. Assistive multimodal system based on speech recognition and head tracking. In 2005 13th European Signal Processing Conference. IEEE, 1--4."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/tap.1986.1143830"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-387"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2007.366327"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/sp-m.2006.248717"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2786219"},{"key":"e_1_3_2_2_27_1","volume-title":"Deep residual network for sound source localization in the time domain. arXiv preprint arXiv:1808.06429","author":"Suvorov Dmitry","year":"2018","unstructured":"Dmitry Suvorov, Ge Dong, and Roman Zhukov. 2018. Deep residual network for sound source localization in the time domain. arXiv preprint arXiv:1808.06429 (2018)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-147"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-403"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/s121013781"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103418"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347954"},{"key":"e_1_3_2_2_33_1","volume-title":"Meeting Transcription Using Virtual Microphone Arrays. arXiv preprint arXiv:1905","author":"Yoshioka Takuya","year":"2019","unstructured":"Takuya Yoshioka, Zhuo Chen, Dimitrios Dimitriadis, William Hinthorn, Xuedong Huang, Andreas Stolcke, and Michael Zeng. 2019. Meeting Transcription Using Virtual Microphone Arrays. arXiv preprint arXiv:1905.02545 (2019)."}],"event":{"name":"CHI '20: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '20","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3313831.3376427","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3313831.3376427","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3313831.3376427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:34Z","timestamp":1750199914000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3313831.3376427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,21]]},"references-count":33,"alternative-id":["10.1145\/3313831.3376427","10.1145\/3313831"],"URL":"https:\/\/doi.org\/10.1145\/3313831.3376427","relation":{},"subject":[],"published":{"date-parts":[[2020,4,21]]},"assertion":[{"value":"2020-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}