Key points are not available for this paper at this time.
Auditory systems are the most efficient and direct strategy for communication between human beings and robots. In this domain, flexible acoustic sensors with magnetic, electric, mechanical, and optic foundations have attracted significant attention as key parts of future voice user interfaces (VUIs) for intuitive human-machine interaction. This study investigated a novel machine learning-based voice recognition platform using an MXene/MoS2 flexible vibration sensor (FVS) with high sensitivity for acoustic recognition. The performance of the MXene/MoS2 FVS was systematically investigated both theoretically and experimentally, and the MXene/MoS2 FVS exhibited high sensitivity (25.8 mV/dB). An MXene/MoS2 FVS with a broadband response of 40–3,000 Hz was developed by designing a periodically ordered architecture featuring systematic optimization. This study also investigated a machine learning-based speaker recognition process, for which a machine-learning-based artificial neural network was designed and trained. The developed neural network achieved high speaker recognition accuracy (99.1%).
Chen et al. (Sat,) studied this question.