The Community for Technology Leaders
RSS Icon
Issue No.04 - July/August (2002 vol.22)
pp: 38-48
Shlomo Dubnov , Ben-Gurion University
Ziv Bar-Joseph , Massachussets Institute of Technology
Ran El-Yaniv , Technion-Israel Institute of Technology
Dani Lischinski , Hebrew University of Jerusalem
Michael Werman , Hebrew University of Jerusalem
<p>In this paper we present a statistical learning algorithm for synthesizing new random instances of a sound texture given an example of such a texture as input. A large class of natural and artificial sounds such as rain, waterfall, traffic noises, people babble, machine noises, etc., can be regarded as sound textures--sound signals that are approximately stationary at some scale. Treating the input sound texture as a sample of a stochastic process, we construct a tree representing a hierarchical wavelet transform of the signal. From this tree, new random trees are generated by learning and sampling the conditional probabilities of the paths in the original tree. Transformation of these random trees back into signals results in new sound textures that closely resemble the sonic impression of the original sound source but without exactly repeating it. Applications of this method are abundant and include, for example, automatic generation of sound effects, creative musical and sonic manipulations, and virtual reality sonification. Examples are visually demonstrated in the paper and acoustically demonstrated in an accompanying web site.</p>
Shlomo Dubnov, Ziv Bar-Joseph, Ran El-Yaniv, Dani Lischinski, Michael Werman, "Synthesizing Sound Textures through Wavelet Tree Learning", IEEE Computer Graphics and Applications, vol.22, no. 4, pp. 38-48, July/August 2002, doi:10.1109/MCG.2002.1016697
1. D. Gabor, "Acoustical Quanta and the Theory of Hearing," Nature, vol. 159, no. 4044, 1947, pp. 591-594.
2. C. Roads, "Introduction to Granular Synthesis," Computer Music J., vol. 12, no. 2, 1988, pp. 11-13.
3. G. De Poli and A. Piccialli, "Pitch-Synchhronous Granular Synthesis," Representation of Musical Signals, G. De Poli, A. Piccialli, and C. Roads, eds., MIT Press, Cambridge, Mass., 1991, pp. 187-219.
4. R. Hoskinson and D. Pai, "Manipulation and Resynthesis with Natural Grains," Int'l Computer Music Conf. (ICMC 01), Int'l Computer Music Assoc., San Francisco, 2001, pp. 338-341.
5. R.O. Duda and P.E. Hart, Pattern Classification and Scene Analysis, John Wiley&Sons, New York, 1973.
6. S. Dubnov, R. El-Yaniv, and G. Assayag, "Universal Classification Applied to Musical Sequences," Proc. Int'l Computer Music Conf. (ICMC 98), Int'l Computer Music Assoc., San Francisco, 1998, pp. 248-254.
7. R. El-Yaniv, S. Fine, and N. Tishby, “Agnostic Classification of Markovian Sequences,” Advances in Neural Information Processing Systems, M.I. Jordan, M.J. Kearns, and S.A. Solla, eds., volume 10, MIT Press, 1998.
8. I. Daubechies, "Orhtonormal Bases of Compactly Supported Wavelets," Communications on Pure and Applied Mathematics, vol. 41, no. 7, Oct. 1988, pp. 909-996.
9. G. Box, G. Jenkins, and G. Reinsel, Time Series Analysis: Forecasting and Control, 3rd ed., Prentice Hall, Englewood Cliffs, N.J., 1994.
10. N. Merhav and M. Feder, “Universal Prediction,” IEEE Trans. Information Theory, vol. 44, no. 6, pp. 2124-2147, 1998.
11. M. Basseville, A. Benveniste, K.C. Chou, S.A. Golden, R. Nikoukhah, and A.S. Willsky, “Modeling and Estimation of Multiresolution Stochastic Processes,” IEEE Trans. Information Theory, vol. 38, no. 2, pp. 766-784, 1992.
12. G.W. Wornell and A.V. Oppenheim, “Wavelet-Based Representations for a Class of Self-Similar Signals with Application to Fractal Modulation,” IEEE Trans. Information Theory, vol. 38, no. 2, pp. 785-800, 1992.
13. Z. Bar-Joseph, R. El-Yaniv, D. Lischinski, and M. Werman, Texture Mixing and Texture Movie Synthesis Using Statistical Learning IEEE Trans. Visualization and Computer Graphics, vol. 7, 2001.
14. R.A. DeVore, B. Jawerth, and B.J. Lucier, “Image Compression through Wavelet Transform Coding,” IEEE Trans. Information Theory, vol. 38, no. 2 (Part II)), pp. 719-746, 1992.
23 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool