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

A critical component in the pattern matching approach to speech recognition is the training
algorithm, which aims at producing typical (reference) patterns or models for accurate …

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 …

The statistical use of a particular classic form of a connectionist system, the multilayer
perceptron (MLP), is described in the context of the recognition of continuous speech. A …

Das Thema der vorliegenden Arbeit ist die Problemstellung maschineller Erkennung
gesprochener Sprache. Ein wichtiger Forschungszweig auf diesem Gebiet ist gegenwärtig …

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

In recent years there has been a significant body of work, both theoretical and experimental,
that has established the viability of artificial neural networks (ANN's) as a useful technology …

Hidden Markov models are widely used for automatic speech recog (cid: 173) nition. They
inherently incorporate the sequential character of the speech signal and are statistically …

Hidden markov models (HMM's) are one of the most powerful speech recognition tools
available today. Even so, the inadequacies of HMM's as a" correct" modeling framework for …