arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02847eess.SP
收藏

SilentWear: 一种超低功耗的可穿戴系统用于基于EMG的静默语音识别

SilentWear: an Ultra-Low Power Wearable System for EMG-based Silent Speech Recognition

Integrated Systems Laboratory of ETH Zürich(苏黎世联邦理工学院集成系统实验室);Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna(博洛尼亚大学电气、电子和信息工程系);Department of Control and Computer Engineering, Politecnico of Turin(都灵理工大学控制与计算机工程系)

Giusy Spacone, Sebastian Frey, Giovanni Pollo, Alessio Burrello, Daniele Jahier Pagliari, Victor Kartsch, Andrea Cossettini, Luca Benini

AI总结:

SilentWear是一种超低功耗可穿戴系统,利用EMG信号实现静默语音识别,通过轻量级CNN架构和边缘计算技术,实现了高准确率和低能耗的实时语音识别。

摘要:

通过生物信号检测语音具有越来越大的关注度,因为其有潜力开发出噪声鲁棒、隐私保护且适用于临床应用和日常使用的计算机接口。然而,大多数现有方法仍然受限于不足的可穿戴性和缺乏边缘处理能力,这对于最小侵入性、响应性和隐私保护的辅助技术至关重要。在本工作中,我们提出了SilentWear,一种完全可穿戴的基于纺织品的颈部接口,用于EMG信号的采集和处理。通过BioGAP-Ultra供电,该系统能够实现从14个差分通道的端到端数据采集和设备端语音识别。SilentWear与SpeechNet相结合,这是一种轻量级的15000参数CNN架构,专门针对基于EMG的语音解码进行优化,实现了在八个代表性的人机交互命令上,语音和静默语音的平均交叉验证准确率分别为84.8±4.6%和77.5±6.6%。我们评估了多日使用引起的重新定位的鲁棒性。在跨会话设置中,系统实现了语音和静默语音的平均准确率分别为71.1±8.3%和59.3±2.2%。为了减轻由于重新定位导致的性能下降,我们提出了一种增量微调策略,证明了通过少于10分钟的额外用户数据可以实现超过10%的准确率恢复。最后,我们展示了在商用多核微控制器(MCU)上的端到端实时设备端语音识别,实现了每推理63.9μJ的能耗和2.47 ms的延迟。总功耗为20.5mW,用于采集、推理和无线传输结果,SilentWear可连续运行超过27小时。

英文摘要:

Detecting speech from biosignals is gaining increasing attention due to the potential to develop human-computer interfaces that are noise-robust, privacy-preserving, and scalable for both clinical applications and daily use. However, most existing approaches remain limited by insufficient wearability and the lack of edge-processing capabilities, which are essential for minimally obtrusive, responsive, and private assistive technologies. In this work, we present SilentWear, a fully wearable, textile-based neck interface for EMG signal acquisition and processing. Powered by BioGAP-Ultra, the system enables end-to-end data acquisition from 14 differential channels and on-device speech recognition. SilentWear is coupled with SpeechNet, a lightweight 15k-parameter CNN architecture specifically tailored for EMG-based speech decoding, achieving an average cross-validated accuracy of 84.8$\pm$4.6% and 77.5$\pm$6.6% for vocalized and silent speech, respectively, over eight representative human-machine interaction commands collected over multiple days. We evaluate robustness to repositioning induced by multi-day use. In an inter-session setting, the system achieves average accuracies of 71.1$\pm$8.3% and 59.3\pm2.2% for vocalized and silent speech, respectively. To mitigate performance degradation due to repositioning, we propose an incremental fine-tuning strategy, demonstrating more than 10% accuracy recovery with less than 10 minutes of additional user data. Finally, we demonstrate end-to-end real-time on-device speech recognition on a commercial multi-core microcontroller unit (MCU), achieving an energy consumption of 63.9$μ$J per inference with a latency of 2.47 ms. With a total power consumption of 20.5mW for acquisition, inference, and wireless transmission of results, SilentWear enables continuous operation for more than 27 hours.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑