GFIS: Genetic Fuzzy Inference System for Speech Recognition

Washington Luis Santos Silva, Ginalber Luiz de Oliveira Serra

Abstract

The concept of fuzzy sets and fuzzy logic is widely used to propose of several methods applied to systems modeling, classification and pattern recognition problem. This paper proposes a genetic-fuzzy recognition system for speech recognition. In addition to pre-processing, with mel-cepstral coefficients, the Discrete Cosine Transform (DCT) is used to generate a two-dimensional time matrix for each pattern to be recognized. A genetic algorithms is used to optimize a Mamdani fuzzy inference system in order to obtain the best model for final recognition. The speech recognition system used in this paper was named Genetic Fuzzy Inference System for Speech Recognition (GFIS). Experimental results for speech recognition applied to brazilian language show the efficiency of the proposed methodology compared to methodologies widely used and cited in the literature.

References

  1. Ahmed, N., Natajaran, T., and Rao, K. R. (1974). Discrete cosine transform. IEEE Transaction on Computers, C-23:90-93.
  2. Andrews, H. C. (1971). Multidimensional rotations in feature selection. IEEE Transaction on Computers, C20:1045-1051.
  3. Ariki, Y., Mizuta, S., Nagata, M., and Sakai, T. (1989). Spoken- word recognition using dynamic features analysed by two-dimensional cepstrum. IEEE Proceedings, 136(v.2):133-140.
  4. Fissore, L., Laface, P., and Rivera, E. (1997). Using word temporal structure in hmm speech recongnition. ICASSP 97, v.2:975-978.
  5. Fu, K. S. (1968). Sequential Methods in Pattern Recognition and Machine Learning. Acadmic Press, New York.
  6. Gang, C. (2010). Discussion of approximation properties of minimum inference fuzzy system. Proceedings of the 29th Chinese Control Conference, pages 2540-2546.
  7. Gosztolya, G., Dombi, J., and Kocsor, A. (2009). Applying the generalized dombi operator family to the speech recognition task. Journal of Computing and Information Technology, pages 285-293.
  8. Haupt, R. L. and Haupt, S. E. (2004). Pratical Genetic Algorithms. John Wiley and Sons, New York.
  9. Milner, B. P., Conner, P. N., and Vaseghi, S. V. (1994). Speech modeling using cepstral-time feature and hidden markov models. Communications, Speech and Vision, IEE Proceedings I, v.140(5):601-604.
  10. Monserrat, M., Torrens, J., and Trillas, E. (2007). A survey on fuzzy implication functions. IEEE Transactions on Fuzzy Systems, v.15(6):1107-1121.
  11. Picone, J. W. (1991). Signal modeling techiniques in speech recognition. IEEE Transactions, v.79:1214-1247.
  12. Rabiner, L. and Hwang, J. B. (1993). Fundamentals of Speech Recognition. Prentice Hall, New Jersey.
  13. Seki, H., Ishii, H., and Mizumoto, M. (2010). On the monotonicity of fuzzy inference methods related to ts inference method. IEEE Transactions on Fuzzy Systems, v.18(3):629-634.
  14. Shenouda, S. D., Zaki, F. W., and Goneid, A. M. R. (2006). Hybrid fuzzy hmm system for arabic connectionist speech recognition. The 23rd National U.Jio Science Conference (NRSC 2006), v.0:1-8.
  15. Silva, W. L. S. and Serra, G. L. O. (2011). Proposta de metodologia tcd-fuzzy para reconhecimento de voz. X SBAI:Simposio Brasileiro de Automacao Inteligente, pages 1054-1059.
  16. Tang, C., Lai, E., and Wang, Y. C. (1997). Distributed fuzzy rules for preprocessing of speech segmentation with genetic algorithm. Fuzzy Systems, Proceedings of the Sixth IEEE International Conference on, v.1:427-431.
  17. Wachter, M., Matton, M., Demuynck, K., Wambacq, P., Cools, R., and Compernolle, D. V. (2007). Templatebased continuous speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, v.15:1377-1390.
  18. Wang, L. X. (1994). A course in Fuzzy Systems and Control. Prentice Hall.
  19. Zhou, J. and Chen, P. (2009). Generalized discrete cosine transform. Circuits, Communications and Systems, PACCS 2009, Pacific Asia Conference on, pages 449- 452.
Download


Paper Citation


in Harvard Style

Luis Santos Silva W. and Serra G. (2012). GFIS: Genetic Fuzzy Inference System for Speech Recognition . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8565-21-1, pages 536-541. DOI: 10.5220/0004045705360541


in Bibtex Style

@conference{icinco12,
author={Washington Luis Santos Silva and Ginalber Luiz de Oliveira Serra},
title={GFIS: Genetic Fuzzy Inference System for Speech Recognition},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2012},
pages={536-541},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004045705360541},
isbn={978-989-8565-21-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - GFIS: Genetic Fuzzy Inference System for Speech Recognition
SN - 978-989-8565-21-1
AU - Luis Santos Silva W.
AU - Serra G.
PY - 2012
SP - 536
EP - 541
DO - 10.5220/0004045705360541