Noisy speech recognition using noise reduction method based on Kalman filter

In this paper, we propose a noise reduction method based on Kalman filter for noisy speech recognition. The proposed method aims to achieve blind source segregation in real time. Since the Kalman filter needs a huge quantity of computation, it was never used for real time processing. Our proposed method using a fast Kalman filter can reduce a large quantity of computation and achieve processing in 1.5-2.0 times of real time, without losing the accuracy. In order to evaluate the proposed method, we carried out experiments to extract clean speech signal from noisy speech and compared the results by our method with conventionally used spectral subtraction and parallel model combination in word recognition accuracy. As a result, the proposed method obtained word recognition rate equal or superior to parallel model combination.