Improved acoustic modeling for speech recognition using 2D Markov random fields

This paper argues that many HMM model inaccuracies are a direct consequence of the fact that the HMM is a one dimensional stochastic model applied to a two dimensional process. Thus we argue that a 2D stochastic process, known as a Markov random field (MRF) should perform better. We describe a training method for MRFs and analyze its convergence behavior.