{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T11:05:26Z","timestamp":1789383926369,"version":"build-2803163510"},"reference-count":41,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:00:00Z","timestamp":1789171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>An intelligent speech sensor is often evaluated at recognition output, although acquisition and preprocessing also determine what reaches control. We examine this propagation in an event-synchronized dual-frontend system. A conditional cascade separates artifact availability, evidence formation, semantic conversion, and executor persistence. It decomposes how scheduled intent survives to the action boundary from raw audio through controlled motion. Paired recordings compare an INMP441\u2013ESP32 interface with a USB interface. In an exploratory study, five speakers each delivered 30 Chinese utterances in three acoustic conditions, giving 450 scheduled events, 1800 ASR paths, and 3600 decision paths. Twelve missing artifacts remained in the intention-to-test denominators. Under the frozen peak normalization rule, isolated full-scale INMP samples limited window gain, and normalized USB\u2013INMP speech-band differences reached +20.96 to +29.52 dB. Mean cloud text availability was 48.0 percentage points higher on USB. Exact valid execution rose by 41.7 points for DeepSeek and by 26.7 points for MiMo. Unauthorized non-stop motion on reject events rose by 19.6 points for DeepSeek and by 13.0 points for MiMo. Capability and risk increased together in all ten cloud speaker\u2013consumer contrasts. Among 564 dangerous reject paths, 340 contained no literal motion token. In the worst case per speaker, hold-last replay produced 72.2\u2013100% dangerous reject states. This is an exploratory sensor system case study of the tested frontend and preprocessing configuration, not a capsule ranking. Preprocessing changed useful evidence reach and action opportunity, so coverage, authorization, and acknowledged executor state need joint evaluation. The empirical results are specific to the tested pipeline and the five observed speakers.<\/jats:p>","DOI":"10.3390\/s26185794","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:19:41Z","timestamp":1789381181000},"page":"5794","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Preprocessing and Capability\u2013Risk Coupling in an Event-Synchronized Dual-Frontend Speech Sensor System"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3167-8148","authenticated-orcid":false,"given":"Hansheng","family":"Chen","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Soochow University, Suzhou 215006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9899-5047","authenticated-orcid":false,"given":"Zhanyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Soochow University, Suzhou 215006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"73890","DOI":"10.1109\/ACCESS.2021.3080517","article-title":"Towards open and expandable cognitive AI architectures for large-scale multi-agent human-robot collaborative learning","volume":"9","author":"Papadopoulos","year":"2021","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Strazdas, D., Hintz, J., Khalifa, A., Abdelrahman, A.A., Hempel, T., and Al-Hamadi, A. (2022). Robot System Assistant (RoSA): Towards intuitive multi-modal and multi-device human\u2013robot interaction. Sensors, 22.","DOI":"10.3390\/s22030923"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TNSRE.2002.1031981","article-title":"Voice control of a powered wheelchair","volume":"10","author":"Simpson","year":"2002","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kiangala, K.S., and Wang, Z. (2022). An experimental safety response mechanism for an autonomous moving robot in a smart manufacturing environment using Q-learning algorithm and speech recognition. Sensors, 22.","DOI":"10.3390\/s22030941"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.specom.2009.08.002","article-title":"Silent speech interfaces","volume":"52","author":"Denby","year":"2010","journal-title":"Speech Commun."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kim, M., Park, J., Park, K., Lee, Y.-J., and Jeon, S. (2026). Streamlining human\u2013robot interaction: Integrating LLM-based planning into modular robotic frameworks. Sensors, 26.","DOI":"10.3390\/s26061978"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Liang, X., and Cai, J. (2026). A multimodal agentic AI framework for intuitive human\u2013robot collaboration. Sensors, 26.","DOI":"10.36227\/techrxiv.177223092.27607998\/v1"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, D., Wei, Y., Zhang, K., Ji, D., and Wang, Y. (2022). Automatic speech recognition performance improvement for Mandarin based on optimizing gain control strategy. Sensors, 22.","DOI":"10.3390\/s22083027"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bae, S., Kim, H., Lee, S., and Jung, Y. (2023). FPGA implementation of keyword spotting system using depthwise separable binarized and ternarized neural networks. Sensors, 23.","DOI":"10.3390\/s23125701"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1109\/TASLP.2014.2304637","article-title":"An overview of noise-robust automatic speech recognition","volume":"22","author":"Li","year":"2014","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.specom.2004.12.004","article-title":"Confidence measures for speech recognition: A survey","volume":"45","author":"Jiang","year":"2005","journal-title":"Speech Commun."},{"key":"ref_12","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume":"Volume 202","author":"Radford","year":"2023","journal-title":"Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA, 23\u201329 July 2023"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Gao, Z., Zhang, S., McLoughlin, I., and Yan, Z. (2022, January 18\u201322). Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. Proceedings of the Interspeech 2022, Incheon, Republic of Korea.","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, L., Fazel-Zarandi, M., Tiwari, A., Matsoukas, S., and Polymenakos, L. (2020, January 9). Data augmentation for training dialog models robust to speech recognition errors. Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, Online.","DOI":"10.18653\/v1\/2020.nlp4convai-1.8"},{"key":"ref_15","unstructured":"Shapira, O., Chazan, S.E., and Cohen, A.D.N. (August, January 27). Measuring the effect of transcription noise on downstream language understanding tasks. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Everson, K., Gu, Y., Yang, H., Shivakumar, P.G., Lin, G.-T., Kolehmainen, J., Bulyko, I., Gandhe, A., Ghosh, S., and Hamza, W. (2024, January 14\u201319). Towards ASR-robust spoken language understanding through in-context learning with word confusion networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.","DOI":"10.1109\/ICASSP48485.2024.10447938"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1162\/TACL.a.628","article-title":"VoiceBench: Benchmarking LLM-based voice assistants","volume":"14","author":"Chen","year":"2026","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_18","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume":"Volume 205","author":"Ichter","year":"2023","journal-title":"Proceedings of the 6th Conference on Robot Learning, Auckland, New Zealand, 14\u201318 December 2022"},{"key":"ref_19","unstructured":"Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., and Zeng, A. (June, January 29). Code as policies: Language model programs for embodied control. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), London, UK."},{"key":"ref_20","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume":"Volume 202","author":"Driess","year":"2023","journal-title":"Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA, 23\u201329 July 2023"},{"key":"ref_21","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume":"Volume 205","author":"Huang","year":"2023","journal-title":"Proceedings of the 6th Conference on Robot Learning, Auckland, New Zealand, 14\u201318 December 2022"},{"key":"ref_22","first-page":"661","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","volume":"Volume 229","author":"Ren","year":"2023","journal-title":"Proceedings of the 7th Conference on Robot Learning, Atlanta, GA, USA, 6\u20139 November 2023"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/TIT.1970.1054406","article-title":"On optimum recognition error and reject tradeoff","volume":"16","author":"Chow","year":"1970","journal-title":"IEEE Trans. Inf. Theory."},{"key":"ref_24","unstructured":"Geifman, Y., and El-Yaniv, R. (2017, January 4\u20139). Selective classification for deep neural networks. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_25","unstructured":"Angelopoulos, A.N., Bates, S., Fisch, A., Lei, L., and Schuster, T. (2024, January 7\u201311). Conformal risk control. Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478535","article-title":"Distribution-free, risk-controlling prediction sets","volume":"68","author":"Bates","year":"2021","journal-title":"J. ACM"},{"key":"ref_27","unstructured":"Quach, V., Fisch, A., Schuster, T., Yala, A., Sohn, J.H., Jaakkola, T., and Barzilay, R. (2024, January 7\u201311). Conformal language modeling. Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bohus, D., and Rudnicky, A.I. (2005, January 6\u20138). Error handling in the RavenClaw dialog management architecture. Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, Vancouver, BC, Canada.","DOI":"10.3115\/1220575.1220604"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Seto, D., Krogh, B., Sha, L., and Chutinan, A. (1998, January 24\u201326). The Simplex architecture for safe on-line control system upgrades. Proceedings of the 1998 American Control Conference, Philadelphia, PA, USA.","DOI":"10.1109\/ACC.1998.703255"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1145\/2723871","article-title":"Real-time reachability for verified Simplex design","volume":"15","author":"Johnson","year":"2016","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"ref_31","unstructured":"(2025). Robotics\u2014Safety Requirements\u2014Part 2: Industrial Robot Applications and Robot Cells (Standard No. ISO 10218-2:2025)."},{"key":"ref_32","unstructured":"(2015). Safety of Machinery\u2014Emergency Stop Function\u2014Principles for Design (Standard No. ISO 13850:2015)."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, K., Hao, Y., Wang, Y., Lai, Z., Guimbreti\u00e8re, F., and Zhang, C. (2023, January 23\u201328). EchoSpeech: Continuous silent speech recognition on minimally-obtrusive eyewear powered by acoustic sensing. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, Hamburg, Germany.","DOI":"10.1145\/3544548.3580801"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Caro-Via, S., Vida\u00f1a-Vila, E., Ginovart-Panisello, G.J., Mart\u00ednez-Suqu\u00eda, C., Freixes, M., and Alsina-Pag\u00e8s, R.M. (2022). Edge-computing meshed wireless acoustic sensor network for indoor sound monitoring. Sensors, 22.","DOI":"10.3390\/s22187032"},{"key":"ref_35","first-page":"3956282","article-title":"A survey of sound source localization methods in wireless acoustic sensor networks","volume":"1","author":"Cobos","year":"2017","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Gori, G., Papini, M., and Fantechi, A. (2025). Efficient reliability block diagram evaluation through improved algorithms and parallel computing. Appl. Sci., 15.","DOI":"10.3390\/app152111397"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1121\/1.405631","article-title":"The Lombard reflex and its role on human listeners and automatic speech recognizers","volume":"93","author":"Junqua","year":"1993","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_38","unstructured":"(2026). DeepSeek-V4: Towards highly efficient million-token context intelligence. arXiv."},{"key":"ref_39","unstructured":"Xiaomi MiMo Team (2026). Full-pipeline inference optimization for MiMo-V2.5 series: Pushing hybrid SWA efficiency to the limit. arXiv."},{"key":"ref_40","unstructured":"Willard, B.T., and Louf, R. (2023). Efficient guided generation for large language models. arXiv."},{"key":"ref_41","unstructured":"Min, A., Hu, C., Ren, Y., and Zhao, H. (2025). When end-to-end is overkill: Rethinking cascaded speech-to-text translation. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5794\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:21:35Z","timestamp":1789381295000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,12]]},"references-count":41,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185794"],"URL":"https:\/\/doi.org\/10.3390\/s26185794","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,12]]}}}