We have described some of the problems with modeling mixed acoustic signals in the log
spectral domain using graphical models, as well as some current approaches to handling …

This paper proposes an acoustic modeling approach based on bootstrap and restructuring
to dealing with data sparsity for low-resourced languages. The goal of the approach is to …

We present a new method for multi-talker speech recognition using a single-channel that
combines loopy belief propagation and variational inference methods to control the …

In probabilistic modeling, it is often useful to change the structure, or refactor, a model, so
that it has a different number of components, different parameter sharing, or other …

Access is obtained to a large reference acoustic model for automatic speech recognition.
The large reference acoustic model has L states modeled by L mixture models, and the …

Variational KL (varKL) divergence minimization was previously applied to restructuring
acoustic models (AMs) using Gaussian mixture models by reducing their size while …

Embedding a large vocabulary speech recognition system in mobile devices requires a
reduced acoustic model obtained by eliminating redundant model parameters. In …

Recently, kernel eigenvoices were revisited using kernel representations of distributions for
rapid nonlinear speaker adaptation. These representations reassure the validity of the …

ABSTRACT A problem often encountered in probabilistic modeling is restructuring a model
to change its number of components, parameter sharing, or some other structural …

This paper describes optimization methods of acoustic models in HMM-based continuous
speech recognition. Most of the conventional speech recognition systems use the same …