Graphical models for integrating syllabic information

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.