Multi‐channel underdetermined blind source separation for recorded audio mixture signals using an unmanned aerial vehicle

Abstract

Unmanned aerial vehicles as an important role for 5G and beyond networks are becoming more and more popular and have been equipped with various sensors to enable diverse emerging applications, e.g. locating sound-emitting targets. Multi-channel blind source separation algorithm has been applied into the unmanned aerial vehicles and micro aerial vehicles, where underdetermined mixture blind source separation is a challenging problem, i.e. the number of sources is more than the number of microphones. An optimization underdetermined blind source separation algorithm to separate the multi-channel audio mixture signals recorded by an unmanned aerial vehicle is proposed. In the algorithm, firstly a hierarchical clustering to estimate channel as the mixing matrix initialization is employed, while using direction of arrival permutation algorithm to deal with the permutation alignment and update the mixing matrix using multiplication update method. Then the model parameters are estimated using improved expectation-maximization update rules for the fast convergence. Finally, the frequency-domain sources are estimated through Wiener filtering and time-domain sources are obtained via inverse short-time Fourier transform. Experimental results covering synthetic and real-recorded speech source mixtures show that the proposed algorithm achieves better separation results than the state-of-the-art methods. INTRODUCTIONUnmanned aerial vehicles (UAVs) have been playing an important role for 5G and beyond networks [1, 2], which can be equipped with microphones or cameras, and have been used to execute critical real-time tasks in our daily lives. For example, multi-rotor micro aerial vehicles (MAVs) can be equipped with microphones to locate sound-emitting targets. However, the received data collected by the MAVs are complex and changeable, which need to be processed for further real-time data analysis. Additionally, the microphones move together with the MAV, thus leading to a dynamic acoustic mixing network. To deal with this problem, blind source separation (BSS) method is separating source signals from multi-channel observations of mixture signals without any prior information on chan-This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

A Robust Hybrid Neural Network Architecture for Blind Source Separation of Speech Signals Exploiting Deep Learning

“…The need to support ultra-high data rates, massive connectivity, low latency, improved spectral efficiency, enhanced quality-of-service (QOS), and diverse services necessitates the exploration of advanced signal processing techniques [1], [2]. Blind source separation (BSS) emerges as a promising approach to address these challenges by leveraging the capability to separate mixed source signals and extract valuable information from complex mixtures [3], [4].…”