Speech Recognition in a Noisy Environment Using a Speech Signal Estimation Method Based on the Kalman Filter

摘要

This paper proposes a speech signal estimation method based on the Kalman filter, as preprocessing for speech recognition in a noisy environment. Hitherto, the Kalman filter has been considered unsuited to real-time processing, since it requires a tremendous amount of computation. Consequently, the purpose of this paper is to reduce the amount of computation in the Kalman filter and to propose a speech signal estimation method for real-time processing, using high-speed operation. In order to evaluate the proposed method, a word recognition experiment was performed, using a speech signal extracted from speed with superposed noise. The accuracy of the word recognition tests is compared to the conventional spectral subtraction method and the parallel model combination method in order to demonstrate that the proposed method can deal automatically with various kinds of stationary noise without manual adjustment of the filter parameters for the conditions, such as the speaker, the kind of noise, and the SNR. For this purpose, the range of noise compensation by the proposed method is investigated. It is verified that the proposed method achieves a high word recognition rate, even in the presence of noise that degraded the recognition rate in the conventional method. In particular, the proposed method is effective in environments with a low SNR.