{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T06:46:01Z","timestamp":1782369961863,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST Moonshot R&D Grant","award":["JPMJMS2012"],"award-info":[{"award-number":["JPMJMS2012"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791397","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:26Z","timestamp":1776053546000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NasoVoce: A Nose-Mounted Low-Audibility Speech Interface for Always-Available Speech Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-2514","authenticated-orcid":false,"given":"Jun","family":"Rekimoto","sequence":"first","affiliation":[{"name":"Sony Computer Science Laboratories, Kyoto, Kyoto, Kyoto, Japan and The University of Tokyo, Bunkyo-ku, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3978-6917","authenticated-orcid":false,"given":"Yu","family":"Nishimura","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9378-2555","authenticated-orcid":false,"given":"Bojian","family":"Yang","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2001. Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs."},{"key":"e_1_3_3_2_3_2","volume-title":"Use Voice Isolation, Wide Spectrum, or Automatic Mic Mode on your iPhone and iPad","author":"Inc. Apple","year":"2025","unstructured":"Apple Inc.2025. Use Voice Isolation, Wide Spectrum, or Automatic Mic Mode on your iPhone and iPad. https:\/\/support.apple.com\/en-us\/101993 Accessed: 2025-11-29."},{"key":"e_1_3_3_2_4_2","unstructured":"Yannis\u00a0M. Assael Brendan Shillingford Shimon Whiteson and Nando de Freitas. 2016. LipNet: End-to-End Sentence-level Lipreading. arxiv:https:\/\/arXiv.org\/abs\/1611.01599\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1611.01599"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Fei\u00a0C. Chen Estella P.-M. Ma and Edwin M.-L. Yiu. 2014. Facial Bone Vibration In Resonant Voice Production. Journal of Voice 28 5 (2014) 596\u2013602. 10.1016\/j.jvoice.2013.12.014","DOI":"10.1016\/j.jvoice.2013.12.014"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Adiba\u00a0Tabassum Chowdhury Mehrin Newaz Purnata Saha Mohannad\u00a0Natheef AbuHaweeleh Sara Mohsen Diala Bushnaq Malek Chabbouh Raghad Aljindi Shona Pedersen and Muhammad E.\u00a0H. Chowdhury. 2025. Decoding silent speech: a machine learning perspective on data methods and frameworks. Neural Computing and Applications 37 10 (2025) 6995\u20137013. 10.1007\/s00521-024-10456-z","DOI":"10.1007\/s00521-024-10456-z"},{"key":"e_1_3_3_2_7_2","unstructured":"Aref Farhadipour Homa Asadi and Volker Dellwo. 2024. Leveraging Self-Supervised Models for Automatic Whispered Speech Recognition. arxiv:https:\/\/arXiv.org\/abs\/2407.21211\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2407.21211"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242603"},{"key":"e_1_3_3_2_9_2","unstructured":"Sanchit Gandhi Patrick von Platen and Alexander\u00a0M. Rush. 2023. Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling. arxiv:https:\/\/arXiv.org\/abs\/2311.00430\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2311.00430"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596832"},{"key":"e_1_3_3_2_11_2","unstructured":"Geoffrey\u00a0E. Hinton Oriol Vinyals and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network.CoRR abs\/1503.02531 (2015). http:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1503.html#HintonVD15"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652920.3652925"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3721185"},{"key":"e_1_3_3_2_14_2","unstructured":"Wei-Ning Hsu Benjamin Bolte Yao-Hung\u00a0Hubert Tsai Kushal Lakhotia Ruslan Salakhutdinov and Abdelrahman Mohamed. 2021. HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units. (June 2021). arxiv:https:\/\/arXiv.org\/abs\/2106.07447\u00a0[cs.CL]"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Boyan Huang Baiyu Liu Shuai Zhang Zhijun Zhang Tao Zhang Wenqi Jia Shiming Zhang Yifeng Lin and Tetsuya Shimamura. 2024. Online bone\/air-conducted speech fusion in the presence of strong narrowband noise. Signal Processing 225 (2024) 109615. 10.1016\/j.sigpro.2024.109615","DOI":"10.1016\/j.sigpro.2024.109615"},{"key":"e_1_3_3_2_17_2","unstructured":"Prolific inc.2014. Prolific. https:\/\/www.prolific.co"},{"key":"e_1_3_3_2_18_2","unstructured":"jfsantos. 2019. mushraJS. https:\/\/github.com\/jfsantos\/mushraJS"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172977"},{"key":"e_1_3_3_2_20_2","unstructured":"Yoon Kim and Alexander\u00a0M. Rush. 2016. Sequence-Level Knowledge Distillation. arxiv:https:\/\/arXiv.org\/abs\/1606.07947\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1606.07947"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Tatsuya Kitamura. 2012. Measurement of vibration velocity pattern of facial surface during phonation using scanning vibrometer. Acoustical Science and Technology 33 2 (2012) 126\u2013128.","DOI":"10.1250\/ast.33.126"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Kelan Kuang Feiran Yang and Jun Yang. 2024. A lightweight speech enhancement network fusing bone- and air-conducted speech. The Journal of the Acoustical Society of America 156 2 (2024) 1355\u20131366. 10.1121\/10.0028339","DOI":"10.1121\/10.0028339"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"H\u00e9ctor A.\u00a0Cordourier Maruri Paulo Lopez-Meyer Jonathan Huang Willem\u00a0Marco Beltman Lama Nachman and Hong Lu. 2018. V-Speech: Noise-Robust Speech Capturing Glasses Using Vibration Sensors. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2 4 Article 180 (Dec. 2018) 23\u00a0pages. 10.1145\/3287058","DOI":"10.1145\/3287058"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"J. Moon. 1990. The influence of nasal patency on accelerometric transduction of nasal bone vibration. The Cleft palate journal 27 3 (1990) 266\u2013274. 10.1597\/1545-1569(1990)027<0266:tionpo>2.3.co;2","DOI":"10.1597\/1545-1569(1990)027<0266:tionpo>2.3.co;2"},{"key":"e_1_3_3_2_26_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Tao Xu Greg Brockman Christine McLeavey and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. arxiv:https:\/\/arXiv.org\/abs\/2212.04356\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2212.04356"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580706"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699374"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581465"},{"key":"e_1_3_3_2_31_2","unstructured":"surfing.ai. 2018. ST-AEDS-20180100_1 Free ST American English Corpus. https:\/\/openslr.org\/45\/."},{"key":"e_1_3_3_2_32_2","unstructured":"Syntiant. 2024. SiSonic Surface Mount MEMS Microphones. https:\/\/www.syntiant.com\/mems."},{"key":"e_1_3_3_2_33_2","unstructured":"Syntiant. 2024. V2S Voice Vibration Sensor. https:\/\/www.syntiant.com\/v2s."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Cees\u00a0H. Taal Richard\u00a0C. Hendriks Richard Heusdens and Jesper Jensen. 2011. An Algorithm for Intelligibility Prediction of Time\u2013Frequency Weighted Noisy Speech. IEEE Transactions on Audio Speech and Language Processing 19 7 (2011) 2125\u20132136. 10.1109\/TASL.2011.2114881","DOI":"10.1109\/TASL.2011.2114881"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888480"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"J. Thiemann N. Ito and E. Vincent. 2013. DEMAND: a collection of multi-channel recordings of acoustic noise in diverse environments. 21st International Congress on Acoustics (ICA 2013) (2013). 10.5281\/zenodo.1227121","DOI":"10.5281\/zenodo.1227121"},{"key":"e_1_3_3_2_38_2","unstructured":"International\u00a0Telecommunication Union. 2013. BS.1534 : Method for the subjective assessment of intermediate quality level of audio systems. https:\/\/www.itu.int\/rec\/R-REC-BS.1534\/en"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Heming Wang Xueliang Zhang and DeLiang Wang. 2022. Fusing Bone-Conduction and Air-Conduction Sensors for Complex-Domain Speech Enhancement. IEEE\/ACM Transactions on Audio Speech and Language Processing 30 (2022) 3134\u20133143. 10.1109\/TASLP.2022.3209943","DOI":"10.1109\/TASLP.2022.3209943"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Lei Wang Xingwei Wang Xi Zhang Xiaolei Ma Yu Zhang Fusang Zhang Tao Gu and Haipeng Dai. 2025. AccCall: Enhancing Real-time Phone Call Quality with Smartphone\u2019s Built-in Accelerometer. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9 3 Article 133 (Sept. 2025) 33\u00a0pages. 10.1145\/3749463","DOI":"10.1145\/3749463"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Mou Wang Junqi Chen Xiaolei Zhang Zhiyong Huang and Susanto Rahardja. 2022. Multi-modal speech enhancement with bone-conducted speech in time domain. Applied Acoustics 200 (2022) 109058. 10.1016\/j.apacoust.2022.109058","DOI":"10.1016\/j.apacoust.2022.109058"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642092"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"E.\u00a0M. Yiu F.\u00a0C. Chen G. Lo and G. Pang. 2012. Vibratory and perceptual measurement of resonant voice. Journal of voice 26 5 (2012). 10.1016\/j.jvoice.2012.02.005","DOI":"10.1016\/j.jvoice.2012.02.005"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Cheng Yu Kuo-Hsuan Hung Syu-Siang Wang Szu-Wei Fu Yu Tsao and Jeih-Weih Hung. 2020. Time-Domain Multi-modal Bone\/air Conducted Speech Enhancement. IEEE Signal Processing Letters 27 (2020) 1035\u20131039. 10.1109\/LSP.2020.3000968","DOI":"10.1109\/LSP.2020.3000968"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580801"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Yi Zhou Yufan Chen Yongbao Ma and Hongqing Liu. 2020. A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor. Sensors 20 18 (2020) 5050. 10.3390\/s20185050","DOI":"10.3390\/s20185050"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:48:57Z","timestamp":1782366537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791397"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":45,"alternative-id":["10.1145\/3772318.3791397","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791397","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}