Audio Commands Recognition Through Deep Learning for Control Mobile Residential Assistant Robot

Abstract

This article exposes the training of a convolutional neural network to recognize voice commands that allow an assistant robot to use in a residential environment. Given the needs for isolation due to health factors, development of care robots that can support a human presents a necessary research focus. For this case, the performance of the network is evaluated, which presents a 94.33% accuracy in the recognition of voice commands, through a virtual environment of a co n ventio na l residence.