ARMA modelling based on root cepstral deconvolution

S. Sarpal1, E. Chilton1
1Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK

Tóm tắt

Cepstral deconvolution has been successfully applied to many diverse fields, such as speech and seismic analysis. Thus far, all cepstral modelling performance has been empirical, relying on the judgement of the designer. A novel method for measuring root cepstral ARMA modelling performance is proposed, by introducing a cost function applied directly to the root cepstral domain. It is, therefore, possible to demonstrate the optimised modelling of an ARMA process and show that its performance is superior to that of a FIR Wiener filter and linear prediction.

Từ khóa

#Cepstral analysis #Deconvolution #Autoregressive processes #Cepstrum #Poles and zeros #Speech analysis #Wiener filter #Speech processing #Predictive models #Finite impulse response filter

Tài liệu tham khảo

kondoz, 1999, Digital Speech Coding for Low Bit Rate Digital Communication Systems 10.1109/78.934138 lim, 1979, Spectral Root Homomorphic Deconvolution System, ASSP-27 No 3, 223, 10.1109/TASSP.1979.1163234 deller, 2000, Discrete-Time Processing of Speech Signals 10.1109/78.575712 hayes, 1996, Statistical Digital Signal Processing and Modeling