Analysis of speech signals’ characteristics based on MF-DFA with moving overlapping windows

In this paper, multi-fractal characteristics of speech signals are analyzed based on MF-DFA, and it is found that the multi-fractal features are influenced greatly by frame length and noise, besides, there is a little difference between them among speech frames. Secondly, motivated by framing and using frame shift to ensure the continuity and smooth transition of speech in speech signals processing, an advanced MF-DFA (MF-DFA with forward moving overlapping windows) is proposed. The length of moving overlapping windows is determined by parameter θ. Given the value of time scale s, we have MF-DFA with the maximum moving overlapping windows and MF-DFA with half overlapping windows when θ=1/s and θ=1/2 respectively. Moreover, when θ=1 we exactly have MF-DFA. Numerical experiments and analysis illustrate that the multi-fractal characteristics based on AMF-DFA outperform MF-DFA and MF-DMA in stability, noise immunity and discrimination.

[1]  Masahiro Nakagawa,et al.  The fractal properties of vocal sounds and their application in the speech recognition model , 1996 .

[2]  R. Ellis.  The bluefin in peril. , 2008, Scientific American.

[3]  B. Mandelbrot.  A Multifractal Walk down Wall Street , 1999 .

[4]  Xiongwei Zhang,et al.  Research on Speaker Recognition Based on Multifractal Spectrum Feature , 2010, 2010 Second International Conference on Computer Modeling and Simulation.

[7]  Witold Kinsner,et al.  Speech segmentation using multifractal measures and amplification of signal features , 2008, 2008 7th IEEE International Conference on Cognitive Informatics.

[8]  Witold Kinsner,et al.  Consonant characterization using correlation fractal dimension for speech recognition , 1995, IEEE WESCANEX 95. Communications, Power, and Computing. Conference Proceedings.

[9]  Wang Conghui.  Speech emotion recognition based on multifractal , 2012 .

[10]  H. Stanley,et al.  Multifractal Detrended Fluctuation Analysis of Nonstationary Time Series , 2002, physics/0202070.

[11]  Rosângela Coelho,et al.  Text-independent speaker recognition based on the Hurst parameter and the multidimensional fractional Brownian motion model , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[12]  Petros Maragos,et al.  Fractal aspects of speech signals: dimension and interpolation , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[13]  Wei-Xing Zhou,et al.  Detrending moving average algorithm for multifractals. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  Diana Cristina González,et al.  Analysis of the Multifractal Nature of Speech Signals , 2012, CIARP.