Joint uncertainty decoding for noise robust speech recognition

Background noise can have a significant impact on the performance of speech recognition systems. A range of fast featurespace and model-based schemes have been investigated to increase robustness. Model-based approaches typically achieve lower error rates, but at an increased computational load compared to feature-based approaches. Thismakes their use inmany situations impractical. The uncertainty decoding framework can be considered an elegant compromise between the two. Here, the uncertainty of features is propagated to the recogniser in a mathematically consistent fashion. The complexity of themodel used to determine the uncertaintymay be decoupled from the recognition model itself, allowing flexibility in the computational load. This paper describes a new approach within this framework, Joint uncertainty decoding. This approach is compared with the uncertainty decoding version ofSPLICE, standardSPLICE, and a new form of front-end CMLLR. These are evaluated on a medium vocabulary speech recognition task with artificially added noise.