Abstract
This paper discusses application of fractal dimensions to speech processing. Generalized dimensions of arbitrary orders and associated fractal parameters are used in speaker identification. A characteristic vactor based on these parameters is formed, and a recognition criterion definded in order to identify individual speakers. Experimental results show the usefulness of fractal dimensions in characterizing speaker identity.
Similar content being viewed by others
References
Maragos P. Fractal aspects of speech signals: dimension and interpolation [J]. Proc. IEEE ICASSP, 1991, 1: 417–420.
Tomeas T J. A finite element model of fluid flow in the vocal tract[J]. Comput. Speech Language,1986, 1: 131–151.
Mandelbrot B B. The Fractal Geometry of Nature[M]. W. H. Freeman, NY, 1982.
Theiler J. Estimating fractal dimension [J]. J. Opt. Soc. Am., 1990, A7(6): 1055–1073.
Mees A I, Rapp P E, Jenning L S. Singular-value decomposition and embedding dimension [J]. Phys. Rev., 1987, A36(2): 340–346.
Packard NH, et al. Geometry from a time series [J]. Phys. Rev. Lett., 1983, 45: 712–720.
Grassberger P, Procaccia I. Measuring the strangeness of strange attractor [J]. Phys. Rev. Lett., 1983, 50: 346.
Grassberger P, Procaccia I. Generalization dimension of fractal attractors [J]. Phys. Lett., 1983, A97: 227–230.
Renyi A. Probability Theory [M]. North Holland, Amsterdam, 1970.
Atmanspacher H, et al., Global scaling properties of chaotic attractor reconstructed form experimental data [J]. Phys. Rev., 1988, A37: 1314–1322.
Author information
Authors and Affiliations
Additional information
Project supported by the Key Disciplinary Development Program of Shanghai, and the Science Foundation of Shanghai Municipal Commission of Education (Grant No.81769)
About this article
Cite this article
Hou, LM., Wang, SZ. Speaker identification based on fractal dimensions. J. of Shanghai Univ. 7, 60–63 (2003). https://doi.org/10.1007/s11741-003-0053-4
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/s11741-003-0053-4