This tutorial provides an overview of the basic theory of hidden Markov models (HMMs) as
originated by LE Baum and T. Petrie (1966) and gives practical details on methods of …

A description is given of SPHINX, a system that demonstrates the feasibility of accurate,
large-vocabulary, speaker-independent, continuous speech recognition. SPHINX is based …

In this paper we present a Time-Delay Neural Network (TDNN) approach to phoneme
recognition which is characterized by two important properties. 1) Using a 3 layer …

Connectionist Speech Recognition: A Hybrid Approach describes the theory and
implementation of a method to incorporate neural network approaches into state of the art …

Hidden Markov modeling is extended to speaker-independent phone recognition. Using
multiple codebooks of various linear-predictive-coding (LPC) parameters and discrete …

Composed of three sections, this book presents the most popular training algorithm for
neural networks: backpropagation. The first section presents the theory and principles …

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 …

Markov models are extremely useful as a general, widely applicable tool for many areas in
statistical pattern recognition. This unique text/reference places the formalism of Markov …

In order for speech recognizers to deal with increased task perplexity, speaker variation, and
environment variation, improved speech recognition is critical. Steady progress has been …

The authors are concerned with integrating connectionist networks into a hidden Markov
model (HMM) speech recognition system. This is achieved through a statistical interpretation …