Development of robust VAD schemes for Voice Operated Switch application in aircrafts: Comparison of real-time VAD schemes which are based on Linear Energy-based Detector, Fuzzy Logic and Artificial Neural Networks

In a fighter aircraft, for the optimal usage of resources during transmission of signals, a Voice Operated Switch (VOS) is used, as it is considered as a better option compared to push to talk (PTT), because it gives hands free environment for the pilot to carry out other crucial tasks. The heart of VOS is a Voice Activity Detection (VAD) algorithm. This paper explores the evolution of a reliable, robust VAD scheme for VOS application in aircraft by comparing real-time robust VAD schemes, which are based on energy-based detectors, fuzzy logic and ANN. MATLAB, is used as the simulation platform and actual fighter aircraft cockpit noise record is used for evaluation of the algorithms.