4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Optimal Filtering and Smoothing for Speech Recognition using a Stochastic Target Model

Gordon Ramsay, Li Deng

Department of Electrical & Computer Engineering, University of Waterloo, Waterloo, Ontario, Canada

This paper presents a stochastic target model of speech production, where articulator motion in the vocal tract is represented by the state of a Markov-modulated linear dynamical system, driven by a piecewise-deterministic control trajectory, and observed through a non-linear function representing the articulatory-acoustic mapping. Optimal filtering and smoothing algorithms for estimating the hidden states of the model from acoustic measurements are derived using a measure-change technique, and require solution of recursive integral equations. A sub-optimal approximation is developed, and illustrated using examples taken from real speech.

Full Paper

Bibliographic reference.  Ramsay, Gordon / Deng, Li (1996): "Optimal filtering and smoothing for speech recognition using a stochastic target model", In ICSLP-1996, 1113-1116.