A codec for speech recognition in a wireless system

We consider a distributed speech recognition system where representative parameters of the speech signal are extracted at the wireless terminal and transmitted to a centralized automatic speech recognition (ASR) server. Several error protection schemes are proposed for the ASR feature stream. In addition, a "soft-feature" error concealment strategy is introduced at the ASR server that uses the marginal distribution of only the reliable features during likelihood computation. The performance of the error protection and concealment schemes is evaluated over typical cellular wireless channels and it is shown to reduce ASR error rate up to 65% for certain channels.