Microphone-Independent Robust Signal Processing Using Probabilistic Optimum Filtering

Leonardo Neumeyer, Mitch Weintraub

Abstract: A new mapping algorithm for speech recognition relates the features of simultaneous recordings of clean and noisy speech. The model is a piecewise nonlinear transformation applied to the noisy speech feature. The transformation is a set of multidimensional linear least-squares filters whose outputs are combined using a conditional Gaussian model. The algorithm was tested using SRI's DECIPHER™ speech recognition system [1-5]. Experimental results show how the mapping is used to reduce recognition errors when the training and testing acoustic environments do not match.