Ultrathin Eardrum-Inspired Self-Powered Acoustic Sensor for Vocal Synchronization Recognition with the Assistance of Machine Learning

With the rapid development of human-machine interfaces, artificial acoustic sensors play an important role in the hearing impaired. Here, an ultrathin eardrum-like triboelectric acoustic sensor (ETAS) is presented consisting of silver-coated nanofibers, whose thickness is only 40 mu m. The sensitivity and frequency response range of the ETAS are closely related to the geometric parameters. The ETAS endows a high sensitivity of 228.5 mV Pa-1 at 95 dB, and the ETAS has a broad frequency response ranging from 20 to 5000 Hz, which can be tuned by adjusting the thickness, size, or shape of the sensor. Cooperating with artificial intelligence (AI) algorithms, the ETAS can achieve real-time voice conversion with a high identification accuracy of 92.64%. Under good working property and the AI system, the ETAS simplifies signal processing and reduces the power consumption. This work presents a strategy for self-power auditory systems, which can greatly accelerate the miniaturization of self-powered systems used in wearable electronics, augmented reality, virtual reality, and control hubs for automation.

Automated summary

This study presents an ultrathin eardrum-like triboelectric acoustic sensor (ETAS), which has high sensitivity and a broad frequency response range that can be adjusted by geometric parameters. When used in combination with artificial intelligence algorithms, the ETAS can achieve real-time voice conversion with high identification accuracy.