{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T05:45:11Z","timestamp":1778305511844,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":110,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2238553"],"award-info":[{"award-number":["2238553"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2401415"],"award-info":[{"award-number":["2401415"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2403528"],"award-info":[{"award-number":["2403528"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010336","name":"Hellman Foundation","doi-asserted-by":"publisher","award":["Hellman Fellows Award"],"award-info":[{"award-number":["Hellman Fellows Award"]}],"id":[{"id":"10.13039\/100010336","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,4]]},"DOI":"10.1145\/3666025.3699374","type":"proceedings-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:48:26Z","timestamp":1730746106000},"page":"784-798","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Unvoiced: Designing an LLM-assisted Unvoiced User Interface using Earables"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0144-7931","authenticated-orcid":false,"given":"Tanmay","family":"Srivastava","sequence":"first","affiliation":[{"name":"Stony Brook University, Stony Brook, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0162-0052","authenticated-orcid":false,"given":"Prerna","family":"Khanna","sequence":"additional","affiliation":[{"name":"Stony Brook University, Stony Brook, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3226-2318","authenticated-orcid":false,"given":"Shijia","family":"Pan","sequence":"additional","affiliation":[{"name":"University of California Merced, Merced, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-4463","authenticated-orcid":false,"given":"Phuc","family":"Nguyen","sequence":"additional","affiliation":[{"name":"UMass Amherst, Massachusetts, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4864-6420","authenticated-orcid":false,"given":"Shubham","family":"Jain","sequence":"additional","affiliation":[{"name":"Stony Brook University, Stony Brook, 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":"10.1145\/3636534.3695908"},{"key":"e_1_3_2_1_2_1","unstructured":"Daniel Adiwardana Minh-Thang Luong David R So Jamie Hall Noah Fiedel Romal Thoppilan Zi Yang Apoorv Kulshreshtha Gaurav Nemade Yifeng Lu et al. 2020. Towards a human-like open-domain chatbot. arXiv preprint arXiv:2001.09977 (2020)."},{"key":"e_1_3_2_1_3_1","unstructured":"Amazon. 2024. Alexa. https:\/\/developer.amazon.com\/en-US\/alexa"},{"key":"e_1_3_2_1_4_1","unstructured":"Amazon. 2024. Alexa Home Assistant. https:\/\/www.home-assistant.io\/integrations\/alexa\/"},{"key":"e_1_3_2_1_5_1","unstructured":"Dario Amodei Rishita Anubhai Eric Battenberg Carl Case Jared Casper Bryan Catanzaro Jingdong Chen Mike Chrzanowski Adam Coates Greg Diamos et al. 2015. Deep speech 2: End-to-end speech recognition in english and mandarin. CoRR abs\/1512.02595 (2015). arXiv preprint arXiv:1512.02595 (2015)."},{"key":"e_1_3_2_1_6_1","unstructured":"Apple. 2024. Siri. https:\/\/www.apple.com\/siri\/"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"e_1_3_2_1_8_1","unstructured":"Encyclopedia Britannica. 2024. Vowel. https:\/\/www.britannica.com\/topic\/vowel"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00075.2011"},{"key":"e_1_3_2_1_10_1","volume-title":"Ultrasound-based articulatory-to-acoustic mapping with WaveGlow speech synthesis. arXiv preprint arXiv:2008.03152","author":"Csap\u00f3 Tam\u00e1s G\u00e1bor","year":"2020","unstructured":"Tam\u00e1s G\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_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.3159"},{"key":"e_1_3_2_1_12_1","unstructured":"Dataquest. 2024. What are Large Language Models (LLMs) and how will they be used in 2024? https:\/\/www.dataquest.io\/blog\/what-are-large-language-models-llms-and-how-will-they-be-used-in-2024\/"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660033"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2244083"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642095"},{"key":"e_1_3_2_1_16_1","unstructured":"Ecobee. 2024. Ecobee Camera. https:\/\/www.ecobee.com\/en-us\/cameras\/smart-camera-with-voice-control\/"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1159\/000066067"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22020649"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568530"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3419170"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.445"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411830"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2757263"},{"key":"e_1_3_2_1_24_1","volume-title":"Jos\u00e9 L P\u00e9rez-C\u00f3rdoba, and Angel M Gomez.","author":"Gonzalez-Lopez Jose A","year":"2020","unstructured":"Jose A Gonzalez-Lopez, Alejandro Gomez-Alanis, Juan M Mart\u00edn Do\u00f1as, Jos\u00e9 L P\u00e9rez-C\u00f3rdoba, and Angel M Gomez. 2020. Silent speech interfaces for speech restoration: A review. IEEE access 8 (2020), 177995--178021."},{"key":"e_1_3_2_1_25_1","volume-title":"Naveed Akhtar, Jia Wu, Seyedali Mirjalili, et al.","author":"Hadi Muhammad Usman","year":"2023","unstructured":"Muhammad Usman Hadi, Rizwan Qureshi, Abbas Shah, Muhammad Irfan, Anas Zafar, Muhammad Bilal Shaikh, Naveed Akhtar, Jia Wu, Seyedali Mirjalili, et al. 2023. Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects. Authorea Preprints (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2265378"},{"key":"e_1_3_2_1_27_1","volume-title":"Boosting large language model for speech synthesis: An empirical study. arXiv preprint arXiv:2401.00246","author":"Hao Hongkun","year":"2023","unstructured":"Hongkun Hao, Long Zhou, Shujie Liu, Jinyu Li, Shujie Hu, Rui Wang, and Furu Wei. 2023. Boosting large language model for speech synthesis: An empirical study. arXiv preprint arXiv:2401.00246 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458709.3458985"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in natural language processing. Science 349, 6245","author":"Hirschberg Julia","year":"2015","unstructured":"Julia Hirschberg and Christopher D Manning. 2015. Advances in natural language processing. Science 349, 6245 (2015), 261--266."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.02.001"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378192"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.11.004"},{"key":"e_1_3_2_1_33_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--369."},{"key":"e_1_3_2_1_34_1","volume-title":"Univnet: A neural vocoder with multi-resolution spectrogram discriminators for high-fidelity waveform generation. arXiv preprint arXiv:2106.07889","author":"Jang Won","year":"2021","unstructured":"Won Jang, Dan Lim, Jaesam Yoon, Bongwan Kim, and Juntae Kim. 2021. Univnet: A neural vocoder with multi-resolution spectrogram discriminators for high-fidelity waveform generation. arXiv preprint arXiv:2106.07889 (2021)."},{"key":"e_1_3_2_1_35_1","volume-title":"Statistical methods for speech recognition","author":"Jelinek Frederick","unstructured":"Frederick Jelinek. 1998. Statistical methods for speech recognition. MIT press."},{"key":"e_1_3_2_1_36_1","unstructured":"Daniel Jurafsky and James H Martin. [n. d.]. Speech and Language Processing: An Introduction to Natural Language Processing Computational Linguistics and Speech Recognition."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172977"},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Advanced Engineering, Technology and Applications. Springer, 450--463","author":"Kesgin Himmet Toprak","year":"2023","unstructured":"Himmet Toprak Kesgin and Mehmet Fatih Amasyali. 2023. Iterative mask filling: An effective text augmentation method using masked language modeling. In International Conference on Advanced Engineering, Technology and Applications. Springer, 450--463."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications. 44--49","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--49."},{"key":"e_1_3_2_1_40_1","volume-title":"How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions. arXiv preprint arXiv:2406.14805","author":"Kharchenko Julia","year":"2024","unstructured":"Julia Kharchenko, Tanya Roosta, Aman Chadha, and Chirag Shah. 2024. How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions. arXiv preprint arXiv:2406.14805 (2024)."},{"key":"e_1_3_2_1_41_1","unstructured":"Kia. 2024. Kia Voice Control. http:\/\/webmanual.kia.com\/STD_GEN5_WIDE\/AVNT\/EU\/English\/voicerecognitionsystem.html"},{"key":"e_1_3_2_1_42_1","volume-title":"Levine (Eds.)","volume":"36","author":"Kim Sungwon","year":"2023","unstructured":"Sungwon Kim, Kevin Shih, rohan badlani, Joao Felipe Santos, Evelina Bakhturina, Mikyas Desta, Rafael Valle, Sungroh Yoon, and Bryan Catanzaro. 2023. P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 74213--74228. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/eb0965da1d2cb3fbbbb8dbbad5fa0bfc-Paper-Conference.pdf"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502015"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642613"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534621"},{"key":"e_1_3_2_1_47_1","volume-title":"Anomaly detection of time series with smoothness-inducing sequential variational auto-encoder","author":"Li Longyuan","year":"2020","unstructured":"Longyuan Li, Junchi Yan, Haiyang Wang, and Yaohui Jin. 2020. Anomaly detection of time series with smoothness-inducing sequential variational auto-encoder. IEEE transactions on neural networks and learning systems 32, 3 (2020), 1177--1191."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3311823.3311831"},{"key":"e_1_3_2_1_49_1","volume-title":"Point and manner of articulation of English consonants and vowels","author":"Lieber Rochelle","unstructured":"Rochelle Lieber. 2009. Point and manner of articulation of English consonants and vowels. Cambridge University Press, xii--xii."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1353\/lan.1978.0066"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485945"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3168253"},{"key":"e_1_3_2_1_53_1","volume-title":"Reflections on mirror neurons and speech perception. Trends in cognitive sciences 13, 3","author":"Lotto Andrew J","year":"2009","unstructured":"Andrew J Lotto, Gregory S Hickok, and Lori L Holt. 2009. Reflections on mirror neurons and speech perception. Trends in cognitive sciences 13, 3 (2009), 110--114."},{"key":"e_1_3_2_1_54_1","volume-title":"Opportunities, Challenges, and Design Guidelines. arXiv preprint arXiv:2309.13879","author":"Mahmood Amama","year":"2023","unstructured":"Amama Mahmood, Junxiang Wang, Bingsheng Yao, Dakuo Wang, and Chien-Ming Huang. 2023. LLM-Powered Conversational Voice Assistants: Interaction Patterns, Opportunities, Challenges, and Design Guidelines. arXiv preprint arXiv:2309.13879 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/765891.765996"},{"key":"e_1_3_2_1_56_1","volume-title":"A speech interface to virtual environments","author":"McGlashan Scott","year":"1996","unstructured":"Scott McGlashan and Tomas Axling. 1996. A speech interface to virtual environments. Swedish Institute of Computer Science (1996)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aac965"},{"key":"e_1_3_2_1_58_1","unstructured":"Meta. 2024. Quest. https:\/\/www.meta.com\/help\/quest\/articles\/in-vr-experiences\/oculus-features\/using-voice-commands\/"},{"key":"e_1_3_2_1_59_1","unstructured":"Microsoft. 2024. Cortana. https:\/\/learn.microsoft.com\/en-us\/hololens\/hololens-cortana"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","unstructured":"Shervin Minaee Tomas Mikolov Narjes Nikzad Meysam Chenaghlu Richard Socher Xavier Amatriain and Jianfeng Gao. [n. d.]. Large Language Models: A Survey. arXiv:2402.06196 [cs] 10.48550\/arXiv.2402.06196","DOI":"10.48550\/arXiv.2402.06196"},{"key":"e_1_3_2_1_61_1","first-page":"285","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Nobuyuki Otsu","year":"1975","unstructured":"Nobuyuki Otsu et al. 1975. A threshold selection method from gray-level histograms. Automatica 11, 285--296 (1975), 23--27.","journal-title":"Automatica"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445565"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642348"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445430"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445430"},{"key":"e_1_3_2_1_66_1","volume-title":"Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779","author":"Park Daniel S","year":"2019","unstructured":"Daniel S Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D Cubuk, and Quoc V Le. 2019. Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.23"},{"key":"e_1_3_2_1_68_1","unstructured":"Philips. 2024. Philips Samrt Bulbs. https:\/\/t.ly\/Q4JED"},{"key":"e_1_3_2_1_69_1","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society.","author":"Povey Daniel","year":"2011","unstructured":"Daniel Povey, Arnab Ghoshal, Gilles Boulianne, Lukas Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlicek, Yanmin Qian, Petr Schwarz, et al. 2011. The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"e_1_3_2_1_71_1","volume-title":"Fundamentals of speech recognition","author":"Rabiner Lawrence","unstructured":"Lawrence Rabiner and Biing-Hwang Juang. 1993. Fundamentals of speech recognition. Prentice-Hall, Inc., USA."},{"key":"e_1_3_2_1_72_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, JongWook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_73_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_74_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458709.3458941"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2005.12.009"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550314"},{"key":"e_1_3_2_1_79_1","series-title":"Series B: Biological Sciences 336, 1278","volume-title":"Temporal information in speech: acoustic, auditory and linguistic aspects. Philosophical Transactions of the Royal Society of London","author":"Rosen Stuart","year":"1992","unstructured":"Stuart Rosen. 1992. Temporal information in speech: acoustic, auditory and linguistic aspects. Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences 336, 1278 (1992), 367--373."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161187"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/2634317.2634322"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWTA55313.2022.9942730"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550281"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625813"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3678957.3685720"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","unstructured":"Zhiqing Sun Yikang Shen Qinhong Zhou Hongxin Zhang Zhenfang Chen David Cox Yiming Yang and Chuang Gan. [n. d.]. Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision. arXiv:2305.03047 [cs] 10.48550\/arXiv.2305.03047","DOI":"10.48550\/arXiv.2305.03047"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057099"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2016.5"},{"key":"e_1_3_2_1_91_1","unstructured":"Toyota. 2024. Toyota Voice Control. https:\/\/toyota-en-us.visteoninfotainment.com\/how-to-voice-recognition"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON56171.2022.10039985"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3051870"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2021.106763"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369812"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369812"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642092"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.971446"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485937"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00041"},{"key":"e_1_3_2_1_101_1","unstructured":"Yamaha. 2024. Yamaha Sound Bar. https:\/\/usa.yamaha.com\/products\/audio_visual\/sound_bar\/ats-2090\/index.html"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2008.4766822"},{"key":"e_1_3_2_1_103_1","volume-title":"Proceedings of the2006 IJMEINTERTECH Conference","volume":"3","author":"Yue Jianping","year":"2006","unstructured":"Jianping Yue. 2006. Spatial visualization by isometric drawing. In Proceedings of the2006 IJMEINTERTECH Conference, Union, New Jersey, Vol. 3."},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.14203\/jet.v21.19-26"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494990"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3594738.3611365"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494987"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580801"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432192"},{"key":"e_1_3_2_1_110_1","volume-title":"Dialogpt: Large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536","author":"Zhang Yizhe","year":"2019","unstructured":"Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2019. Dialogpt: Large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536 (2019)."}],"event":{"name":"SenSys '24: 22nd ACM Conference on Embedded Networked Sensor Systems","location":"Hangzhou China","acronym":"SenSys '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3666025.3699374","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3666025.3699374","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3666025.3699374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:10Z","timestamp":1750295890000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3666025.3699374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":110,"alternative-id":["10.1145\/3666025.3699374","10.1145\/3666025"],"URL":"https:\/\/doi.org\/10.1145\/3666025.3699374","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"}}]}}