Research on intelligent speech recognition algorithm in UAV ground station

Abstract

Human-machine dialogue is one of the important components of realizing the intelligent control of UAV. By identifying the pronunciation of the UAV operator, the UAV can be controlled by voice commands instead of manual operation. This method can reduce the operation errors caused by the distraction of UAV operators and improve the combat effectiveness of UAV.Based on the analysis of the flight and mission control requirements of unmanned UAV, this paper establishes an end-to-end speech recognition method based Deep full convolutional neural network (DFCNN) and link sequence classification (connectionist temporal classification,CTC ) for operators in UAV ground stations. The experimental results show that the proposed method can improve the signal-to-noise ratio and its recognition accuracy, effectively solve the speech recognition problem in the UAV ground station environment, and has high practical application value.