A resonant piezoelectric microphone array for detection of acoustic signatures in noisy environments

Abstract

This paper reports a MEMS acoustic resonator array that improves Automatic Speech Recognition (ASR) and signature detection characteristics in environments with high levels of acoustic interference. The experiments with the acoustic resonator array show an increase of 62.7 percentage points in ASR transcription accuracy for signals buried under noise with -15 dB Signal-to-Noise Ratio (SNR). The results of this study support the development of resonant acoustic sensors for a variety of pattern recognition applications.