{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T12:40:51Z","timestamp":1760013651594,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","funder":[{"name":"JST ACT-X","award":["JPMJAX23KG"],"award-info":[{"award-number":["JPMJAX23KG"]}]},{"name":"JST Moonshot R&D Grant","award":["JPMJMS2012"],"award-info":[{"award-number":["JPMJMS2012"]}]},{"name":"New Energy and Industrial Technology Development Organization","award":["JPNP23025"],"award-info":[{"award-number":["JPNP23025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,16]]},"DOI":"10.1145\/3745900.3746088","type":"proceedings-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T11:36:08Z","timestamp":1760009768000},"page":"333-344","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MaskClip: Detachable Clip-on Piezoelectric Sensing of Mask Surface Vibrations for Real-time Noise-Robust Speech Input"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6543-4593","authenticated-orcid":false,"given":"Hirotaka","family":"Hiraki","sequence":"first","affiliation":[{"name":"The University of Tokyo \/ National Institute of AdvancedScience and Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-2514","authenticated-orcid":false,"given":"Jun","family":"Rekimoto","sequence":"additional","affiliation":[{"name":"The University of Tokyo \/ Sony CSL, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Khamis\u00a0A. Al-Karawi. 2024. Face mask effects on speaker verification performance in the presence of noise. Multimedia Tools and Applications 83 2 (2024) 4811\u20134824. https:\/\/doi.org\/10.1007\/s11042-023-15824-w","DOI":"10.1007\/s11042-023-15824-w"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"B.\u00a0B. Bauer. 1962. A Century of Microphones. Proceedings of the IRE 50 5 (1962) 719\u2013729. https:\/\/doi.org\/10.1109\/JRPROC.1962.288106","DOI":"10.1109\/JRPROC.1962.288106"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2019.8857198"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538933"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Han Ding Yizhan Wang Hao Li Cui Zhao Ge Wang Wei Xi and Jizhong Zhao. 2022. UltraSpeech: Speech Enhancement by Interaction between Ultrasound and Speech. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 6 3 Article 111 (Sept. 2022) 25\u00a0pages. https:\/\/doi.org\/10.1145\/3550303","DOI":"10.1145\/3550303"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642095"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Di Duan Yongliang Chen Weitao Xu and Tianxing Li. 2024. EarSE: Bringing Robust Speech Enhancement to COTS Headphones. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 7 4 Article 158 (Jan. 2024) 33\u00a0pages. https:\/\/doi.org\/10.1145\/3631447","DOI":"10.1145\/3631447"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Di Duan Yongliang Chen Weitao Xu and Tianxing Li. 2024. EarSE: Bringing Robust Speech Enhancement to COTS Headphones. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 7 4 Article 158 (Jan. 2024) 33\u00a0pages. https:\/\/doi.org\/10.1145\/3631447","DOI":"10.1145\/3631447"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Engin Erzin. 2009. Improving Throat Microphone Speech Recognition by Joint Analysis of Throat and Acoustic Microphone Recordings. IEEE Transactions on Audio Speech and Language Processing 17 7 (2009) 1316\u20131324. https:\/\/doi.org\/10.1109\/TASL.2009.2016733","DOI":"10.1109\/TASL.2009.2016733"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242603"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Jose\u00a0A. Gonzalez Lam\u00a0A. Cheah Angel\u00a0M. Gomez Phil\u00a0D. Green James\u00a0M. Gilbert Stephen\u00a0R. Ell Roger\u00a0K. Moore and Ed Holdsworth. 2017. Direct Speech Reconstruction From Articulatory Sensor Data by Machine Learning. IEEE\/ACM Transactions on Audio Speech and Language Processing 25 12 (2017) 2362\u20132374. https:\/\/doi.org\/10.1109\/TASLP.2017.2757263","DOI":"10.1109\/TASLP.2017.2757263"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581295"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Tatsuya Hirahara Makoto Otani Shota Shimizu Tomoki Toda Keigo Nakamura Yoshitaka Nakajima and Kiyohiro Shikano. 2010. Silent-speech enhancement using body-conducted vocal-tract resonance signals. Speech Communication 52 4 (2010) 301\u2013313. https:\/\/doi.org\/10.1016\/j.specom.2009.12.001 Silent Speech Interfaces.","DOI":"10.1016\/j.specom.2009.12.001"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3583936"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652920.3652925"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458709.3458985"},{"key":"e_1_3_3_2_19_2","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Hu Yuchen","year":"2024","unstructured":"Yuchen Hu, Chen Chen, Chao-Han\u00a0Huck Yang, Ruizhe Li, Chao Zhang, Pin-Yu Chen, and Engsiong Chng. 2024. Large Language Models are Efficient Learners of Noise-Robust Speech Recognition. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/doi.org\/10.48550\/arXiv.2401.10446"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Robert Ingalls. 1987. Throat microphone. The Journal of the Acoustical Society of America 81 3 (03 1987) 809\u2013809. https:\/\/doi.org\/10.1121\/1.394659 arXiv:https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/81\/3\/809\/12095011\/809_1_online.pdf","DOI":"10.1121\/1.394659"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Junki Kawaguchi and Mitsuharu Matsumoto. 2022. Noise Reduction Combining a General Microphone and a Throat Microphone. Sensors 22 12 (2022). https:\/\/doi.org\/10.3390\/s2212 s4473","DOI":"10.3390\/s22124473"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3446382.3448363"},{"key":"e_1_3_3_2_23_2","series-title":"(OzCHI \u201919)","first-page":"568","volume-title":"Proceedings of 31st Australian Conference on Human-Computer-Interaction","author":"Kumazaki Ryoga","year":"2020","unstructured":"Ryoga Kumazaki and Akifumi Inoue. 2020. Development and Evaluation of a Mask-Type Display Transforming the Wearer\u2019s Impression. In Proceedings of 31st Australian Conference on Human-Computer-Interaction (Fremantle, WA, Australia) (OzCHI \u201919). Association for Computing Machinery, New York, NY, USA, 568\u2013571. https:\/\/doi.org\/10.1145\/3369457.3369533"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3519391.3519399"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379350.3416134"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Siddique Latif Junaid Qadir Adnan Qayyum Muhammad Usama and Shahzad Younis. 2021. Speech Technology for Healthcare: Opportunities Challenges and State of the Art. IEEE Reviews in Biomedical Engineering 14 (2021) 342\u2013356. https:\/\/doi.org\/10.1109\/RBME.2020.3006860","DOI":"10.1109\/RBME.2020.3006860"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3415255.3422886"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2851-4_2"},{"key":"e_1_3_3_2_29_2","unstructured":"Boon\u00a0Pang Lim. 2010. Computational differences between whispered and non-whispered speech. PhD Thesis UIUC."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Yi Luo and Nima Mesgarani. 2019. Conv-TasNet: Surpassing Ideal Time\u2013Frequency Magnitude Masking for Speech Separation. IEEE\/ACM Transactions on Audio Speech and Language Processing 27 8 (2019) 1256\u20131266. https:\/\/doi.org\/10.1109\/TASLP.2019.2915167","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Andri Mirzal. 2017. NMF versus ICA for blind source separation. Advances in Data Analysis and Classification 11 1 (2017) 25\u201348. https:\/\/doi.org\/10.1007\/s11634-014-0192-4","DOI":"10.1007\/s11634-014-0192-4"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1200069"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379350.3416137"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Muhammed\u00a0Zahid Ozturk Chenshu Wu Beibei Wang Min Wu and K.\u00a0J.\u00a0Ray Liu. 2023. RadioSES: mmWave-Based Audioradio Speech Enhancement and Separation System. IEEE\/ACM Trans. Audio Speech and Lang. Proc. 31 (March 2023) 1333\u20131347. https:\/\/doi.org\/10.1109\/TASLP.2023.3250846","DOI":"10.1109\/TASLP.2023.3250846"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169756"},{"key":"e_1_3_3_2_36_2","series-title":"(ICML\u201923)","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML\u201923). JMLR.org, Article 1182, 27\u00a0pages."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-275"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929478"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576842.3582365"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Antonia Schulte Rodrigo Suarez-Ibarrola Daniel Wegen Philippe-Fabian Pohlmann Elina Petersen and Arkadiusz Miernik. 2020. Automatic speech recognition in the operating room \u2013 An essential contemporary tool or a redundant gadget? A survey evaluation among physicians in form of a qualitative study. Annals of Medicine and Surgery 59 (2020) 81\u201385. https:\/\/doi.org\/10.1016\/j.amsu.2020.09.015","DOI":"10.1016\/j.amsu.2020.09.015"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Shota Shimizu Makoto Otani and Tatsuya Hirahara. 2009. Frequency characteristics of several non-audible murmur (NAM) microphones. Acoustical Science and Technology 30 2 (2009) 139\u2013142. https:\/\/doi.org\/10.1250\/ast.30.139","DOI":"10.1250\/ast.30.139"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448626"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49062-1_10"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Linda\u00a0M. Thibodeau Rachel\u00a0B. Thibodeau-Nielsen Chi Mai\u00a0Q. Tran and Ryan T.\u00a0S. Jacob. 2021. Communicating During COVID-19: The Effect of Transparent Masks for Speech Recognition in Noise. Ear and Hearing 42 4 (Jul 2021) 772\u2013781. https:\/\/doi.org\/10.1097\/AUD.0000000000001065","DOI":"10.1097\/AUD.0000000000001065"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Vishal\u00a0Varun Tipparaju Di Wang Jingjing Yu Fang Chen Francis Tsow Erica Forzani Nongjian Tao and Xiaojun Xian. 2020. Respiration pattern recognition by wearable mask device. Biosensors and Bioelectronics 169 (2020) 112590. https:\/\/doi.org\/10.1016\/j.bios.2020.112590","DOI":"10.1016\/j.bios.2020.112590"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Vishal\u00a0Varun Tipparaju Xiaojun Xian Devon Bridgeman Di Wang Francis Tsow Erica Forzani and Nongjian Tao. 2020. Reliable Breathing Tracking With Wearable Mask Device. IEEE Sensors Journal 20 10 (2020) 5510\u20135518. https:\/\/doi.org\/10.1109\/JSEN.2020.2969635","DOI":"10.1109\/JSEN.2020.2969635"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Joseph\u00a0C. Toscano and Caroline\u00a0M. Toscano. 2021. Effects of face masks on speech recognition in multi-talker babble noise. PLOS ONE 16 2 (Feb 2021) e0246842. https:\/\/doi.org\/10.1371\/journal.pone.0246842","DOI":"10.1371\/journal.pone.0246842"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642057"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/NETACT.2017.8076802"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Mou Wang Junqi Chen Xiao-Lei Zhang and Susanto Rahardja. 2022. End-to-End Multi-Modal Speech Recognition on an Air and Bone Conducted Speech Corpus. IEEE\/ACM Trans. Audio Speech and Lang. Proc. 31 (Nov. 2022) 513\u2013524. https:\/\/doi.org\/10.1109\/TASLP.2022.3224305","DOI":"10.1109\/TASLP.2022.3224305"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584062"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"NAKAJIMA Yoshitaka KASHIOKA Hideki CAMPBELL Nick and SHIKANO Kiyohiro. 2005. Non-Audible Murmur (NAM) Recognition. IEICE TRANSACTIONS on Information and Systems E89-D 1 (2005).","DOI":"10.1093\/ietisy\/e89-d.1.1"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/RADIOELEK.2010.5478597"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Jun Zhang Jingyue Wu Yiyi Qiu Aiguo Song Weifeng Li Xin Li and Yecheng Liu. 2023. Intelligent speech technologies for transcription disease diagnosis and medical equipment interactive control in smart hospitals: A review. Computers in Biology and Medicine 153 (2023) 106517. https:\/\/doi.org\/10.1016\/j.compbiomed.2022.106517","DOI":"10.1016\/j.compbiomed.2022.106517"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Qian Zhang Dong Wang Run Zhao Yinggang Yu and Junjie Shen. 2021. Sensing to Hear: Speech Enhancement for Mobile Devices Using Acoustic Signals. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 5 3 Article 137 (Sept. 2021) 30\u00a0pages.","DOI":"10.1145\/3478093"}],"event":{"name":"AHs 2025: The Augmented Humans International Conference","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Masdar City, Abu Dhabi United Arab Emirates","acronym":"AHs '25"},"container-title":["Proceedings of the Augmented Humans International Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3745900.3746088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T11:59:15Z","timestamp":1760011155000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3745900.3746088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,16]]},"references-count":56,"alternative-id":["10.1145\/3745900.3746088","10.1145\/3745900"],"URL":"https:\/\/doi.org\/10.1145\/3745900.3746088","relation":{},"subject":[],"published":{"date-parts":[[2025,3,16]]},"assertion":[{"value":"2025-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}