We propose to use the Gamma filter as a continuous time spectral feature extractor for the preprocessing of speech signals. The Gamma filter is a simple analog structure which can be implemented as a cascade of identical first order low-pass filters. The filter generates the Poisson moments of the input signal at its taps. These moments carry spectral information about the recent history of the input signal and in return they can be used to construct a time-frequency representation alternative to the conventional methods of the short-term Fourier transform, cepstrum, etc. The appeal of the proposed method comes from the fact that in the analog domain the Poisson moments are readily available as a continuous time electrical signal and can be physically measured rather than computed offline by a digital computer. With this convenience, the speed of the discrete time processor following the preprocessor is independent of the highest frequency of the input signal, but is constrained by the stationarity interval of the signal. The moments can be directly fed into artificial neural networks (ANNs) for tasks like classification and identification of time-varying signals like speech.
[1]
Ganti Prasada Rao,et al.
Identification of Continuous Dynamical Systems
,
1983
.
[2]
J.C. Principe,et al.
Spectral feature extraction using Poisson moments
,
1994,
Proceedings of IEEE Workshop on Neural Networks for Signal Processing.
[3]
Carl de Boor,et al.
A Practical Guide to Splines
,
1978,
Applied Mathematical Sciences.
[4]
Parameter Identification for Linear Time-Varying Dynamic Processes
,
1970
.
[5]
Jose C. Principe,et al.
Isolated-work speech recognition using the focused gamma neural network
,
1994
.
[6]
J.C. Principe,et al.
Analysis of spectral feature extraction using the gamma filter
,
1994,
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).
[7]
J. Pickles.
An Introduction to the Physiology of Hearing
,
1982
.
[8]
José Carlos Príncipe,et al.
The gamma model--A new neural model for temporal processing
,
1992,
Neural Networks.