Host: Japan SOciety for Fuzzy Theory and intelligent informatics
Co-host: The Korea Fuzzy Logic and Intelligent Systems Society, IEEE Computational Intelligence Society, The International Fuzzy Systems Association, 21th Century COE Program "Creation of Agent-Based Social Systems Sciences"
A noise reduction method is proposed to reduce background noise in noisy speech. We have investigated a noise reconstruction system (NRS) based on a linear prediction error filter (LPEF) and a noise reconstruction filter (NRF). An input signal of a LPEF becomes a white signal. Assuming that background noise is generated by exciting a linear system by a white signal, a NRF can reconstruct the background noise from white noise by estimating a noise generating system. However, since a residual speech is included in an input signal of a NRF, it is necessary to use a small step size, which enables us to update coefficients of a NRF without estimating a speech signal. Thus, it is difficult for a NRS to track non-stationary noise. In order to solve the problem, a noise reconstruction system using step size control is proposed. The step size control takes advantage of cross-correlations between input signals and an enhanced speech signal.