Cascade Prediction Filters With Adaptive Zeros to Track the Time-Varying Resonances of the Vocal Tract

In this paper, a simple and reliable technique is proposed to track vocal tract resonances in continuous speech. The approach is based on the use of predictor filters with adaptive zeros whose constrained trajectories guarantee the successful tracking of the frequency and the damping of each resonance. The zeros are adapted using a gradient-based algorithm to minimize an instantaneous prediction residual according to the principle of minimal disturbance yielding an adaptive structure capable of tracking fast-changing resonance parameters.