8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Sparse Gaussian Graphical Models for Speech Recognition

Peter Bell, Simon King

University of Edinburgh, UK

We address the problem of learning the structure of Gaussian graphical models for use in automatic speech recognition, a means of controlling the form of the inverse covariance matrices of such systems. With particular focus on data sparsity issues, we implement a method for imposing graphical model structure on a Gaussian mixture system, using a convex optimisation technique to maximise a penalised likelihood expression. The results of initial experiments on a phone recognition task show a performance improvement over an equivalent full-covariance system.

Full Paper

Bibliographic reference.  Bell, Peter / King, Simon (2007): "Sparse Gaussian graphical models for speech recognition", In INTERSPEECH-2007, 2113-2116.