Speech sound discrimination with genetic programming
The question that we investigate in this paper is, whether it is possible for Genetic Programming to extract certain regularities from raw time series data of human speech. We examine whether a genetic programming algorithm can find programs that are able to discriminate certain spoken vowels and consonants. We present evidence that this can indeed be achieved with a surprisingly simple approach that does not need preprocessing. The data we have collected on the system’s behavior show that even speaker-independent discrimination is possible with GP.
KeywordsGenetic Programming Recognition Rate Finite Impulse Response Automatic Speech Recognition System Machine Code
Unable to display preview. Download preview PDF.
- [BNKF98]Wolfgang Banzhaf, Peter Nordin, Robert Keller, and Frank D. Francone. Genetic Programming — An Introduction. dpunkt/Morgan Kaufmann, Heidelberg/San Francisco, 1998.Google Scholar
- [GR94]Chris Gathercole and Peter Ross. Some training subset selection for supervised learning in genetic programming. In Yuval Davidor, Hans-Paul Schwefel, and Reinhard MÄnner, editors, Parallel Problem Solving from Nature III, volume 866 of Lecture Notes in Computer Science, pages 312–321, Jerusalem, 9–14 October 1994. Springer-Verlag, Berlin, Germany.Google Scholar
- [HP91]Richard A. Haddad and Thomas W. Parsons. Digital signal processing. Theory, applications, and hardware. Electrical engineering, communications, and signal processing series. W H Freeman, New York, NY, 1991.Google Scholar
- [Kin94]K. E. Kinnear, editor. Advances in Genetic Programming. MIT Press, Cambridge, MA, 1994.Google Scholar
- [Koz92]John R. Koza. Genetic Programming — On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA, 1992.Google Scholar
- [MK93]Sanjit K. Mitra and James F. Kaiser, editors. Handbook for digital signal processing. A Wiley-Interscience publication. Wiley, New York, 1993.Google Scholar
- [NB95a]Peter Nordin and Wolfgang Banzhaf. Complexity compression and evolution. In L. Eshelman, editor, Genetic Algorithms: Proceedings of the Sixth International Conference (ICGA95), pages 310–317, Pittsburgh, PA, 15–19 July 1995. Morgan Kaufmann, San Francisco, CA.Google Scholar
- [NB95b]Peter Nordin and Wolfgang Banzhaf. Evolving Turing-complete programs for a register machine with self-modifying code. In L. Eshelman, editor, Genetic Algorithms: Proceedings of the Sixth International Conference (ICGA95), pages 318–325, Pittsburgh, PA, 15–19 July 1995. Morgan Kaufmann, San Francisco, CA.Google Scholar
- [NB95c]Peter Nordin and Wolfgang Banzhaf. Genetic programming controlling a miniature robot. In E. V. Siegel and J. R. Koza, editors, Working Notes for the AAAI Symposium on Genetic Programming, pages 61–67, MIT, Cambridge, MA, 10–12 November 1995. AAAI, Menlo Park, CA.Google Scholar
- [Nor94]Peter Nordin. A compiling genetic programming system that directly manipulates the machine code. In Kenneth E. Kinnear, Jr., editor, Advances in Genetic Programming, chapter 14, pages 311–331. MIT Press, Cambridge, MA., 1994.Google Scholar
- [Nor97]Peter Nordin. Evolutionary Program Induction of Binary Machine Code and its Applications. PhD thesis, University of Dortmund, M"unster, 1997.Google Scholar
- [PFTV88]William H. Press, Brian P. Flannery, Saul A. Teukolsky, and William T. Vetterling. Numerical Recipes in C — The Art of Scientific Computing. Cambridge University Press, Cambridge, 1988.Google Scholar