Switching Dynamic System Models for Speech Articulation and Acoustics

Abstract

A statistical generative model for the speech process is described that embeds a substantially richer structure than the HMM currently in predominant use for automatic speech recognition. This switching dynamic-system model generalizes and integrates the HMM and the piece-wise stationary nonlinear dynamic system (state- space) model. Depending on the level and the nature of the switching in the model design, various key properties of the speech dynamics can be naturally represented in the model. Such properties include the temporal structure of the speech acoustics, its causal articulatory movements, and the control of such movements by the multidimensional targets correlated with the phonological (symbolic) units of speech in terms of overlapping articulatory features.