Microphone-Independent Robust Signal Processing Using Probabilistic Optimum Filtering

MICROPHONE-INDEPENDENT ROBUST SIGNAL PROCESSING USING PROBABILISTIC OPTIMUM FILTERING Leonardo Neumeyer and Mitchel Weintraub SRI International Speech Technology and Research Laboratory 333 Ravenswood Avenue Menlo Park, CA 94025 ABSTRACT A new mapping algorithm for speech recognition relates the fea- tures of simultaneous recordings of clean and noisy speech. The model is a piecewise nonfinear transformation appfied 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 TM 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. 1. INTRODUCTION In many practical situations an automatic speech recognizer has to operate in several different but well-defined acoustic environ- ments. For example, the same recognition task may be imple- mented using different microphones or transmission channels. In this situation it may not be practical to recollect a speech corpus to train the acoustic models of the recognizer. To alleviate this prob- lem, we propose an algorithm that maps speech features between two acoustic spaces. The models of the mapping algorithm are trained using a small database recorded simultaneously in both environments. In the case of steady-state additive homogenous noise, we can derive a MMSE estimate of the clean speech filterbank-log energy features using a model for how the features change in the presence of this noise [6-7]. In these algorithms, the estimated speech spec- trum is a function of the global spectral signal-to-noise ratio (SNR), the instantaneous spectral SNR, and the overall spectral shape of the speech signal. However, after studying simultaneous recordings made with two microphones, we befieve that the rela- tionship between the two simultaneous features is nonlinear. We therefore propose to use a piecewise-nonlinear model to relate the two feature spaces. 1.1. Related Work on Feature Mapping Several algorithms in the literature have focused on experimen- tally training a mapping between the noisy features and the clean features [8-13]. The proposed algorithm differs from previous algorithms in several ways: • The MMSE estimate of the clean speech features in noise is trained experimentally rather than with a model as in [6, 7]. • Several frames are joined together similar to [13]. • The conditional PDF is based on a generic noisy feature not necessarily related to the feature that we are trying to esti- mate. For example, we could condition the estimate of the cepstral energy on the instantaneous spectral SNR vector. • Multidimensional least-squares filters are used for the map- ping transformation. This exploits the correlation of the fea- tures over time and among components of the spectral ,features at the same time. • Linear transformations are combined together without hard decisions. • All delta parameters are computed after mapping the cep- strum and cepstral energy. • The mapping parameters are trained using stereo recordings with two different microphones. Once trained, the mapping parameters are fixed. • The algorithm can either map …

Content truncated to 500 words