We present our work on end-to-end training of acoustic models using the lattice-free
maximum mutual information (LF-MMI) objective function in the context of hidden Markov …

This thesis investigates the use of discriminative criteria for training HMM parameters for
speech recognition, in particular the Maximum Mutual Information (MMI) criterion and a new …

This paper describes, and evaluates on a large scale, the lattice based framework for
discriminative training of large vocabulary speech recognition systems based on Gaussian …

In this article, we studied the objective functions of MMI, MCE, and MPE/MWE for
discriminative learning in sequential pattern recognition. We presented an approach that …

This paper describes a framework for optimising the structure and parameters of a
continuous density HMM-based large vocabulary recognition system using the Maximum …

The minimum classification error (MCE) framework for discriminative training is a simple and
general formalism for directly optimizing recognition accuracy in pattern recognition …

This paper provides a comprehensive introduction to a novel approach to pattern
recognition which is based on the generalized probabilistic descent method (GPD) and its …

We present PyChain, a fully parallelized PyTorch implementation of end-to-end lattice-free
maximum mutual information (LF-MMI) training for the so-called\emph {chain models} in the …

Over the last 20 years, approaches to designing speech and language processing
algorithms have moved from methods based on linguistics and speech science to data …

State-level minimum Bayes risk (sMBR) training has become the de facto standard for
sequence-level training of speech recognition acoustic models. It has an elegant formulation …