{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T23:16:28Z","timestamp":1775085388699,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"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":[[2024,11,4]]},"DOI":"10.1145\/3678957.3685720","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:35:53Z","timestamp":1730262953000},"page":"214-223","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Whispering Wearables: Multimodal Approach to Silent Speech Recognition with Head-Worn Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0144-7931","authenticated-orcid":false,"given":"Tanmay","family":"Srivastava","sequence":"first","affiliation":[{"name":"Computer Science, Stony Brook University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8874-9184","authenticated-orcid":false,"given":"R. Michael","family":"Winters","sequence":"additional","affiliation":[{"name":"Microsoft Research Labs, Microsoft Corporation, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3033-3565","authenticated-orcid":false,"given":"Thomas","family":"Gable","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5576-5236","authenticated-orcid":false,"given":"Yu Te","family":"Wang","sequence":"additional","affiliation":[{"name":"Academia Sinica, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0690-7597","authenticated-orcid":false,"given":"Teresa","family":"LaScala","sequence":"additional","affiliation":[{"name":"Microsoft Research Labs, Microsoft Corporation, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2263-2047","authenticated-orcid":false,"given":"Ivan J.","family":"Tashev","sequence":"additional","affiliation":[{"name":"Microsoft Research Labs, Microsoft Corporation, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2016.7844812"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.1998.727531"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2865609"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2010.86"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-021-00616-0"},{"key":"e_1_3_2_1_6_1","unstructured":"Hang Chen Jun Du Yu Hu Li-Rong Dai Chin-Hui Lee and Bao-Cai Yin. 2020. Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention. arxiv:2012.14360\u00a0[cs.CV]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427314"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274847"},{"key":"e_1_3_2_1_9_1","volume-title":"Ultrasound-based articulatory-to-acoustic mapping with WaveGlow speech synthesis. arXiv preprint arXiv:2008.03152","author":"Csap\u00f3 Tam\u00e1s\u00a0G\u00e1bor","year":"2020","unstructured":"Tam\u00e1s\u00a0G\u00e1bor Csap\u00f3, Csaba Zaink\u00f3, L\u00e1szl\u00f3 T\u00f3th, G\u00e1bor Gosztolya, and Alexandra Mark\u00f3. 2020. Ultrasound-based articulatory-to-acoustic mapping with WaveGlow speech synthesis. arXiv preprint arXiv:2008.03152 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660033"},{"key":"e_1_3_2_1_11_1","volume-title":"Physical therapy for patients with TMD: a descriptive study of treatment, disability, and health status.Journal of orofacial pain 12, 2","author":"Di\u00a0Fabio P","year":"1998","unstructured":"Richard\u00a0P Di\u00a0Fabio. 1998. Physical therapy for patients with TMD: a descriptive study of treatment, disability, and health status.Journal of orofacial pain 12, 2 (1998)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/11494683_28"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284820"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22020649"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411830"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614120"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/NAECON.2015.7443084"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2757263"},{"key":"e_1_3_2_1_19_1","volume-title":"Jos\u00e9\u00a0L P\u00e9rez-C\u00f3rdoba, and Angel\u00a0M Gomez.","author":"Gonzalez-Lopez A","year":"2020","unstructured":"Jose\u00a0A Gonzalez-Lopez, Alejandro Gomez-Alanis, Juan M\u00a0Mart\u00edn Do\u00f1as, Jos\u00e9\u00a0L P\u00e9rez-C\u00f3rdoba, and Angel\u00a0M Gomez. 2020. Silent speech interfaces for speech restoration: A review. IEEE access 8 (2020), 177995\u2013178021."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2265378"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458709.3458985"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.02.001"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.11.004"},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. of ISSP","author":"Hueber Thomas","year":"2008","unstructured":"Thomas Hueber, G\u00e9rard Chollet, Bruce Denby, and Maureen Stone. 2008. Acquisition of ultrasound, video and acoustic speech data for a silent-speech interface application. Proc. of ISSP (2008), 365\u2013369."},{"key":"e_1_3_2_1_25_1","volume-title":"Present, Future, and A Proposed Model. undefined","author":"Jefferson Madeline","year":"2019","unstructured":"Madeline Jefferson. 2019. Usability of Automatic Speech Recognition Systems for Individuals with Speech Disorders: Past, Present, Future, and A Proposed Model. undefined (2019). https:\/\/www.semanticscholar.org\/paper\/Usability-of-Automatic-Speech-Recognition-Systems-A-Jefferson\/73eefd141f43750b3ae0648e6ef099597e24c6c9"},{"key":"e_1_3_2_1_26_1","first-page":"1","article-title":"EarCommand: \" Hearing","volume":"6","author":"Jin Yincheng","year":"2022","unstructured":"Yincheng Jin, Yang Gao, Xuhai Xu, Seokmin Choi, Jiyang Li, Feng Liu, Zhengxiong Li, and Zhanpeng Jin. 2022. EarCommand: \" Hearing\" Your Silent Speech Commands In Ear. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, 2 (2022), 1\u201328.","journal-title":"Your Silent Speech Commands In Ear. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172977"},{"key":"e_1_3_2_1_28_1","volume-title":"NZ) 10","author":"Kaye Rachel","year":"2017","unstructured":"Rachel Kaye, Christopher\u00a0G Tang, and Catherine\u00a0F Sinclair. 2017. The electrolarynx: voice restoration after total laryngectomy. Medical Devices (Auckland, NZ) 10 (2017), 133."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications. 44\u201349","author":"Khanna Prerna","year":"2021","unstructured":"Prerna Khanna, Tanmay Srivastava, Shijia Pan, Shubham Jain, and Phuc Nguyen. 2021. JawSense: recognizing unvoiced sound using a low-cost ear-worn system. In Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications. 44\u201349."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2901271"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502015"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3399715.3399852"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2016.2569160"},{"key":"e_1_3_2_1_35_1","volume-title":"The Lab Streaming Layer for Synchronized Multimodal Recording. bioRxiv","author":"Kothe Christian","year":"2024","unstructured":"Christian Kothe, Seyed\u00a0Yahya Shirazi, Tristan Stenner, David Medine, Chadwick Boulay, Matthew\u00a0I Crivich, Tim Mullen, Arnaud Delorme, and Scott Makeig. 2024. The Lab Streaming Layer for Synchronized Multimodal Recording. bioRxiv (2024), 2024\u201302."},{"key":"e_1_3_2_1_36_1","unstructured":"Mbient Lab. 2020. Mbient IMU. https:\/\/mbientlab.com\/metamotionr\/"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICINIS.2015.35"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3311823.3311831"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737095.2737109"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485945"},{"key":"e_1_3_2_1_41_1","first-page":"1","article-title":"The basics of MEMS IMU\/Gyroscope alignment","volume":"49","author":"Looney Mark","year":"2015","unstructured":"Mark Looney. 2015. The basics of MEMS IMU\/Gyroscope alignment. Analog Dialogue 49 (2015), 1\u20136.","journal-title":"Analog Dialogue"},{"key":"e_1_3_2_1_42_1","volume-title":"Advances in physiological computing","author":"Majaranta P\u00e4ivi","unstructured":"P\u00e4ivi Majaranta and Andreas Bulling. 2014. Eye tracking and eye-based human\u2013computer interaction. In Advances in physiological computing. Springer, 39\u201365."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Hiroyuki Manabe Akira Hiraiwa and Toshiaki Sugimura. 2003. Unvoiced speech recognition using EMG-mime speech recognition. In CHI\u201903 extended abstracts on Human factors in computing systems. 794\u2013795.","DOI":"10.1145\/765891.765996"},{"key":"e_1_3_2_1_44_1","volume-title":"Facial anatomy. Clinics in dermatology 32, 1","author":"Marur Tania","year":"2014","unstructured":"Tania Marur, Yakup Tuna, and Selman Demirci. 2014. Facial anatomy. Clinics in dermatology 32, 1 (2014), 14\u201323."},{"key":"e_1_3_2_1_45_1","unstructured":"Creative Materials. 2024. Conductive Ink. https:\/\/www.creativematerials.com\/applications\/medical-electrodes\/"},{"key":"e_1_3_2_1_46_1","unstructured":"Creative Materials. 2024. Electrically conductive medical electrode ink.https:\/\/server.creativematerials.com\/datasheets\/DS_113_09.pdf"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1177\/154193120805200505"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aac965"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210322"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.smhl.2018.03.001"},{"key":"e_1_3_2_1_51_1","unstructured":"The\u00a0University of Reading. 2021. The production of speech sounds. http:\/\/www.personal.rdg.ac.uk\/\u00a0llsroach\/phon2\/artic-basics.htm"},{"key":"e_1_3_2_1_52_1","volume-title":"Hand gesture recognition based on computer vision: a review of techniques. journal of Imaging 6, 8","author":"Oudah Munir","year":"2020","unstructured":"Munir Oudah, Ali Al-Naji, and Javaan Chahl. 2020. Hand gesture recognition based on computer vision: a review of techniques. journal of Imaging 6, 8 (2020), 73."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445565"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445430"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCA.2012.6179213"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.23"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419197"},{"key":"e_1_3_2_1_58_1","unstructured":"BrainVision Recorder. 2024. BrainVision Recorder. https:\/\/www.brainproducts.com\/downloads\/recorder\/"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458709.3458941"},{"key":"e_1_3_2_1_60_1","volume-title":"Speech is 3x faster than typing for English and Mandarin text entry on mobile devices. arXiv preprint arXiv:1608.07323","author":"Ruan Sherry","year":"2016","unstructured":"Sherry Ruan, Jacob\u00a0O Wobbrock, Kenny Liou, Andrew Ng, and James Landay. 2016. Speech is 3x faster than typing for English and Mandarin text entry on mobile devices. arXiv preprint arXiv:1608.07323 (2016)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2634317.2634322"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym10070232"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWTA55313.2022.9942730"},{"key":"e_1_3_2_1_64_1","unstructured":"SMOOTH-ON. 2024. FlexFoam-iT!\u2122 6 Pillow Soft. https:\/\/www.smooth-on.com\/products\/flexfoam-it-6\/"},{"key":"e_1_3_2_1_65_1","unstructured":"SMOOTH-ON. 2024. FlexFoam-iT!\u2122 6 Pillow Soft Product Review. https:\/\/www.smooth-on.com\/tb\/files\/FLEXFOAM-IT_SERIES.pdf"},{"key":"e_1_3_2_1_66_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6447\u20136456","author":"Son\u00a0Chung Joon","year":"2017","unstructured":"Joon Son\u00a0Chung, Andrew Senior, Oriol Vinyals, and Andrew Zisserman. 2017. Lip reading sentences in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6447\u20136456."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550281"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450645"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057099"},{"key":"e_1_3_2_1_71_1","volume-title":"Fundamentals of EEG measurement. Measurement science review 2, 2","author":"Michal Teplan","year":"2002","unstructured":"Michal Teplan 2002. Fundamentals of EEG measurement. Measurement science review 2, 2 (2002), 1\u201311."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2517630"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369812"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/29933.275627"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2008.4766822"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494990"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3594738.3611365"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580801"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432192"}],"event":{"name":"ICMI '24: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"San Jose Costa Rica","acronym":"ICMI '24"},"container-title":["International Conference on Multimodel Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685720","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678957.3685720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:12Z","timestamp":1750295412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":79,"alternative-id":["10.1145\/3678957.3685720","10.1145\/3678957"],"URL":"https:\/\/doi.org\/10.1145\/3678957.3685720","relation":{},"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"2024-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}