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

Most contemporary laboratory recognizers require too much memory to run, and are too
slow for mass applications. One major cause of the problem is the large parameter space of …

Automatic speech recognition is a key technology for enabling rich human-computer
interaction in emerging applications. Hidden Markov Model (HMM) based recognition …

Recently, there has been interest in the use of classifiers based on the product of experts
(PoE) framework. PoEs offer an alternative to the standard mixture of experts (MoE) …

This paper introduces a new form of observation distributions for hidden Markov models
(HMMs), combining subvector quantization and mixtures of discrete distributions. We …

This paper introduces a new form of observation distributions for hidden Markov models
(HMMs), combining subvector quantization and mixtures of discrete distributions. Despite …

This paper proposes the use of Quantized Hidden Markov Models (QHMMs) for reducing the
footprint of conventional parametric HMM-based TTS system. Previously, this technique was …

Speech recognition is concerned with converting the speech waveform, an acoustic signal,
into a sequence of words. Today's most practical approaches are based on a statistical …

The problem of clustering Gaussian distributions can be effectively solved by standard
vector quantization algorithms where the metric is defined by the Bhattacharyya distance …

In typical speech recognition systems, there is a dichotomy between speaker independent
and speaker-dependent systems. While speaker-independent system are ready to be used …