Fractal dimension segmentation: isolated speech recognition

This paper investigates the use of fractal geometry for segmenting digital signals. A method of texture segmentation is introduced which is based on the fractal dimension. Using this approach, variations in texture across a signal or image can be characterized in terms of variations in the fractal dimension. By analyzing the spatial fluctuations in fractal dimension obtained using a conventional moving window approach, a digital signal or image can be texture segmented; this is the principle of fractal dimension segmentation (FDS). In this paper, we apply this form of texture segmentation to isolated speech signals. An overview of methods for computing the fractal dimension is presented focusing on an approach that makes use of the characteristic power density function (PSDF) of a random scaling fractal signal. FDS is applied to a number of different speech signals and the results discussed for isolated words and the components (e.g. fricatives) from which these words are composed. In particular, it is shown that by pre-filtering speech signals with a low-pass filter of the form 1/k. This provides confidence in the approach to speech segmentation considered in this paper and in principle, allows a template matching scheme to be designed that is based exclusively on FDS