Title: Time-varying noise compensation by sequential Monte Carlo method

Authors: Kaisheng Yao, Satoshi Nakamura

Abstract: We present a sequential Monte Carlo method applied to additive noise compensation for robust speech recognition in time-varying noise. At each frame, the method generates a set of samples, approximating the posterior distribution of speech and noise parameter given observation sequences till the current frame. Explicit model representing noise effects on speech features is used, so that an extended Kalman filter is constructed in each sample, generating updated continuous state as the estimation of the noise parameter, and prediction likelihood as the weight of each sample for minimum mean square error inference of the timevarying noise parameter over these samples. A selection step and a smoothing step are used to improve efficiency. Through experiments, we observed significant performance improvements, over that achieved by noise compensation with stationary noise assumption. It also performed better than the sequential EM algorithm in Machinegun noise.

a01ky056.ps a01ky056.pdf