Application of polynomial splines to a time-varying autoregressive model of speech

Author

Flaherty, Michael J.

Author_Institution

Telecom Australia Res. Labs., Clayton, Vic., Australia

fYear

1988

fDate

11-14 Apr 1988

Firstpage

2220

Abstract

An investigation is conducted into the use of polynomial spines in a time-varying autoregressive model of speech. The form of the model and computational considerations are discussed. Results are presented for the analysis of synthetic signals and real speech. The effects of model parameters, in particular, spline order and knot spacing, are discussed. The spectral evolution as provided by this model is compared with the more conventional stationary models. The performance of this model for tracking time-varying autoregressive coefficients is compared with the models which use an orthogonal time-series expansion of autoregressive coefficients

Keywords

speech analysis and processing; splines (mathematics); time series; time-varying systems; computational considerations; knot spacing; model parameters; orthogonal time-series expansion; polynomial splines; spectral evolution; speech model; spline order; synthetic signals; time-varying autoregressive model; tracking; Australia; Computational modeling; Laboratories; Polynomials; Predictive models; Signal analysis; Speech analysis; Speech synthesis; Spline; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.197076

Filename

197076