The Centre for Speech Technology Research, The university of Edinburgh

BARKS

Project Summary

The BARKS project is exploring the use of switching linear dynamic models for automatic speech recognition.

Project Details

BARKS stands for 'Better Recognition through Kalman Switching'

This project concerns the application of linear dynamic models (LDM) to automatic speech recognition (ASR). The LDM is a generative model which gives a time-varying multivariate Gaussian distribution over the observations. Underlying dynamics are modelled by the state, which evolves according to a first-order auto-regressive (AR) process. The potential benefits of using such a model for ASR compared to hidden Markov models (HMM) include:

Previous work has demonstrated a benefit from the addition of a hidden dynamic state. The current project extends this by developing a switching system which will allow: