NLMS-Supported Decoding of High-Quality Speech for Burst Channels

For wireless transmission systems for high-quality digital speech signals a low end-to-end delay is desired. Furthermore, signals transmitted over wireless channels may suffer from error bursts which would lead to sustained periods of annoying artifacts if no appropriate error concealment strategies are employed. In this contribution we present a Bayesian approach to delayless soft-decision speech decoding for wireless burst channels which can be applied to, e. g., wireless microphones. Besides channel reliability information we only exploit residual redundancy in the speech signal for the computation of prediction probabilities within a Bayesian framework. In contrast to existing (narrowband) speech error concealment techniques, we employ higher-order adaptive predictors in order to compute the prediction probabilities in this work. Simulations with representative speech data transmitted over burst channels demonstrate a notable increase in signal quality.