Dynamic Bayesian Network Inversion for Robust Speech Recognition

Abstract

This paper presents an inversion algorithm for dynamic Bayesian networks towards robust speech recognition, namely DBNI, which is a generalization of hidden Markov model inversion (HMMI). As a dual procedure of expectation maximization (EM)-based model reestimation, DBNI finds the 'uncontaminated' speech by moving the input noisy speech to the Gaussian means under the maximum likelihood (ML) sense given the DBN models trained on clean speech. This algorithm can provide both the expressive advantage from DBN and the noise-removal feature from model inversion. Experiments on the Aurora 2.0 database show that the hidden feature model (a typical DBN for speech recognition) with the DBNI algorithm achieves superior performance in terms of word error rate reduction.