Improved maximum model distance for HMM training

摘要

A new approach based on the maximum model distance (IMMD) approach for HMM speech recognition systems is proposed. It defines a more realistic model distance definition for HMM training, and utilises the limited training data in a more effective manner. Theoretical and practical issues concerning this approach are investigated. Experimental results showed that a significant reduction in errors could be achieved with this new approach when compared with the maximum model distance (MMD) criterion.