UWEE Tech Report Series

Graphical Models for Integrating Syllabic Information


Chris D. Bartels and Jeff A. Bilmes

speech recognition, graphical models, dynamic Bayesian networks, syllables


We present graphical models that enhance a speech recognizer with information about syllabic segmentations. The segmentations are specified by locations of syllable nuclei, and the graphical models are able to use these locations to specify a "soft" segmentation of the speech data. The graphs give improved discrimination between speech and noise when compared to a baseline model. When using locations derived from oracle information an overall improvement is given, and when the oracle syllable nuclei are augmented with information about lexical stress it gives additional improvements over locations alone.

Download the PDF version