Analysis and classification of speech signals by generalized fractal dimension features

Abstract

We explore nonlinear signal processing methods inspired by dynamical systems and fractal theory in order to analyze and characterize speech sounds. A speech signal is at first embedded in a multidimensional phase-space and further employed for the estimation of measurements related to the fractal dimensions. Our goals are to compute these raw measurements in the practical cases of speech signals, to further utilize them for the extraction of simple descriptive features and to address issues on the efficacy of the proposed features to characterize speech sounds. We observe that distinct feature vector elements obtain values or show statistical trends that on average depend on general characteristics such as the voicing, the manner and the place of articulation of broad phoneme classes. Moreover the way that the statistical parameters of the features are altered as an effect of the variation of phonetic characteristics seem to follow some roughly formed patterns. We also discuss some qualitative aspects concerning the linear phoneme-wise correlation between the fractal features and the commonly employed mel-frequency cepstral coefficients (MFCC) demonstrating phonetic cases of maximal and minimal correlation. In the same context we also investigate the fractal features' spectral content, in terms of the most and least correlated components with the MFCC.

Feature selection for spontaneous speech analysis to aid in Alzheimer's disease diagnosis: A fractal dimension approach

“…In general, fractal dimensions can be utilized to quantify the complexity, concerning the geometry of a dynamical system given its multidimensional phasespace. This quantification is related to the active degrees of freedom of the assumed dynamical system, providing a quantitative characterization of a system's state (Pitsikalis and Maragos, 2009;Maragos and Potamianos, 1999).…”

Phoneme Generation with Elman-type Neural Networks

“…Recently, a new direction of research started towards developing models based on the nonlinear dynamics of speech. Different approaches have been suggested which are based on the identification of the nonlinear type of the vocal dynamics [4][5][6].…”

Combining Mel Frequency Cepstral Coefficients and Fractal Dimensions for Automatic Speech Recognition

“…In contrast, the ASR tasks that have to deal with a very large vocabulary, with under-resourced languages [2], or with noisy environments have to try alternative techniques. An interesting set of alternatives come in the form of nonlinear analysis [3], and some works [4,5,6] show that combining nonlinear features with MFCC's can produce higher recognition accuracies without substituting the whole linear system with novel nonlinear approaches.…”

“…The interest on fractals in speech date back to the mid-80's [7], and they have been used for a variety of applications, including consonant/vowel characterization [8,9], speaker identification [10], and end-point detection [11], even for whispered speech [12]. Indeed, this metric has been also used in speech recognition, in some cases combined with MFCC's as described above [4]. Remarkably, the more notable contributions to the enhancement of ASR using fractals and other nonlinear and chaotic systems features have been made by the Computer Vision, Speech Communication, and Signal Processing Group of the National Technical University of Athens [4,13,14,15,16].…”

“…Indeed, this metric has been also used in speech recognition, in some cases combined with MFCC's as described above [4]. Remarkably, the more notable contributions to the enhancement of ASR using fractals and other nonlinear and chaotic systems features have been made by the Computer Vision, Speech Communication, and Signal Processing Group of the National Technical University of Athens [4,13,14,15,16].…”