Research of detecting fatigue from speech by PNN

Fatigue is a natural phenomenon which is a kind of self-regulation and protection for human body. Detection fatigue states have positive significance for all occupations now. This paper presents a feature-based parameters and the probabilistic neural network (PNN) speech recognition model to detect fatigue. Through training at different times of voice samples as the voice sources and establishing a comprehensive identification system. Experimental results show that this way can reflect the degree of fatigue. MFCC parameters is superior to LPCC.