Research on controller fatigue state detection based on speech spectrogram

Abstract

In the current research on the fatigue state of controllers using radiotelephony communication, most of them only consider the changes of voice in the time domain or frequency domain, while ignore that fatigue will affect the time domain and frequency domain at the same time. The voice of radiotelephony communication in the three fatigue states is converted into speech spectrum images that can reflect the characteristics of both the time domain and frequency domain, and the grayscale co-existence matrix is used to extract the typical feature parameters in four dimensions. The changes of the characteristic parameters of the controllers in different states are compared, and the controller fatigue detection model is constructed to detect the input features. The results show that the detection accuracy of using the spectrogram features combined with the traditional features as the input features is the highest(95.49%), which is 4% higher than that of the traditional features alone. The change of controllers fatigue state can intuitively reflected on the spectrogram and haves an impact on its eigenvalues, and the better detection results can be obtained by using this influence to detect the controllers fatigue state.

Keywords

• controller
• fatigue detection
• spectrogram
• grayscale co-existence matrix
• machine learning