5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Recovering Vocal Tract Shapes from MFCC Parameters

Sorin Dusan, Li Deng

University of Waterloo, E&CE, Waterloo, Ontario N2L 3G1, Canada

Recovering vocal tract shapes from the speech signal is a well known inversion problem of transformation from the articulatory system to speech acoustics. Most of the studies on this problem in the past have been focused on vowels. There have not been general methods effective for recovering the vocal tract shapes from the speech signal for all classes of speech sounds. In this paper we describe our attempt towards speech inverse mapping by using the mel-frequency cepstrum coefficients to represent the acoustic parameters of the speech signal. An inversion method is developed based on Kalman filtering and a dynamic-system model describing the articulatory motion. This method uses an articulatory-acoustic codebook derived from Maeda's articulatory model.

Full Paper

Bibliographic reference.  Dusan, Sorin / Deng, Li (1998): "Recovering vocal tract shapes from MFCC parameters", In ICSLP-1998, paper 0367.