Calculation of Analogs for the Largest Lyapunov Exponents for Acoustic Data by Means of Artificial Neural Networks

A method for calculating the largest Lyapunov exponents analogs for the numerical series obtained from acoustic experimental data is proposed. It is based on the use of artificial neural networks for constructing special additional series which are necessary in the process of calculating the Lyapunov exponents. The musical compositions have been used as acoustic data. It turned out that the error of the largest Lyapunov exponent computations within a single musical composition is sufficiently small. On the other hand for the compositions with different acoustic content there were obtained various numerical values Lyapunov exponents. This enables to make conclusion that the proposed procedure for calculating the Lyapunov exponents is adequate. It also allows to use the obtained results as an additional macroscopic characteristics of acoustic data for comparative analysis.

[1]  Beth Logan,et al.  Mel Frequency Cepstral Coefficients for Music Modeling , 2000, ISMIR.

[2]  Bokyung Sung.  A Feature Based Music Content Recognition method using Simplified MFCC , 2008 .

[3]  G. Benettin,et al.  Lyapunov Characteristic Exponents for smooth dynamical systems and for hamiltonian systems; A method for computing all of them. Part 2: Numerical application , 1980 .

[4]  Ulrich Parlitz,et al.  Comparison of Different Methods for Computing Lyapunov Exponents , 1990 .

[5]  M. Rosenstein,et al.  A practical method for calculating largest Lyapunov exponents from small data sets , 1993 .

[6]  Brown,et al.  Computing the Lyapunov spectrum of a dynamical system from an observed time series. , 1991, Physical review. A, Atomic, molecular, and optical physics.

[7]  H. Kantz.  A robust method to estimate the maximal Lyapunov exponent of a time series , 1994 .

[8]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[9]  Eckmann,et al.  Liapunov exponents from time series. , 1986, Physical review. A, General physics.

[10]  Sawada,et al.  Measurement of the Lyapunov spectrum from a chaotic time series. , 1985, Physical review letters.

[11]  Tom J. Moir,et al.  Kepstrum approach to real-time speech-enhancement methods using two microphones , 2005 .

[12]  H. Kantz,et al.  Nonlinear time series analysis , 1997 .

[13]  G. Benettin,et al.  Lyapunov Characteristic Exponents for smooth dynamical systems and for hamiltonian systems; a method for computing all of them. Part 1: Theory , 1980 .

[14]  Qingyang Hong,et al.  Using Mel-Frequency Cepstral Coefficients in Missing Data Technique , 2004, EURASIP J. Adv. Signal Process..

[15]  A. B. Potapov,et al.  On the concept of stationary Lyapunov basis , 1998 .

[16]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.