Drone audition: improved Gaussian mixture model Wiener filtering approach for audio signal enhancement

Abstract

Audio signal enhancement is an integral function of drone audition systems which emerges intelligent audio applications for military and civil environments. Signal enhancement using a drone is challenging due to its emission of significant noise from drone motors and propellers resulting in an extremely low signal-to-drone noise ratio level. A method for signal enhancement from an on-board microphone array on a drone for static flight conditions in adverse noisy environments is proposed. In this paper, we present an improved Gaussian mixture model Wiener filter approach for a noisy drone platform in the presence of interfering noise sources such as wind, and traffic. The key to this method is to exploit the spatial properties of the noise sources by using a set of Gaussian components to derive an accurate estimate of the power spectral densities of both residual drone noise and interfering noise sources to obtain the enhanced target sound source signal. We demonstrate the method's general applicability for both speech, and bird calls using an extensive experimental study, including an experimental recording from a drone acoustics dataset using measured impulse responses, and an outdoor measurement from a hovering drone for a bioacoustic application, respectively.