Study on the Chinese continuous speech recognition under noise environments based on PCANN/HMM

This paper presents a method to improve the noise robustness of the Chinese continuous speech recognition system based on the PCANN/HMM hybrid structure. By using principal components combined by successive multi-frames as the input of HMM, it utilizes the dependency between frames to reduce the influence of noise effectively. And in this paper, we also improve the traditional spectral subtraction (SS) method. Experimental results demonstrate the efficiency of the new algorithms in Chinese continuous speech recognition under high noisy environments.