This paper examines the application of linear transformations for speaker and environmental
adaptation in an HMM-based speech recognition system. In particular, transformations that …

There is normally a simple choice made in the form of the covariance matrix to be used with
continuous-density HMMs. Either a diagonal covariance matrix is used, with the underlying …

One of the key issues for adaptation algorithms is to modify a large number of parameters
with only a small amount of adaptation data. Speaker adaptation techniques try to obtain …

In recent years, considerable progress has been made in the eld of continuous speech
recognition where the predominant technology is based on hidden Markov models (HMMs) …

Advances in speech technology and computing power have created a surge of interest in
the practical application of speech recognition. However, the most accurate speech …

This thesis details the development of a model-based noise compensation technique,
Parallel Model Combination (PMC). The aim of PMC is to alter the parameters of a set of …

In automatic speech recognition (ASR) systems, the speech signal is captured and
parameterized at front end and evaluated at back end using the statistical framework of …

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 past decade (1990-2000) has witnessed substantial advances in speech recognition
technology, which when combined with the increase in computational power and storage …

The maximum likelihood linear regression (MLLR) approach for speaker adaptation of
continuous density mixture Gaussian HMMs is presented and its application to static and …