Kotelnikov Institute of Radio Engineering and Electronics of RAS Русский Sign in Submit a paper
Journal of Radio Electronics Online scientific journal · eISSN 1684-1719
2009, № 7 · MATHEMATICAL MODELS IN RADIO ELECTRONICS PROBLEMS

Speaker Independent Speech Recognition System Using Neural Networks

N. Uma Maheswari1, A.P. Kabilan2, R. Venkatesh3

1 Senior Lecturer, Dept. of CSE, P.S.N.A College of Engg& Technology, Dindigul-624622,India, India
2 Principal, Chettinad college of Engg& Technology, Karur-639114,India, India
3 Senior Lecturer, Dept. of CSE, R.V.S College of Engg& Technology, Dindigul-624005,India, India
Full text (PDF) EDN KUICYF

Abstract

Speaker independent speech recognition is important for successful development of speech recognizers in most real world applications. While speaker dependent speech recognizers have achieved close to 100% accuracy, the speaker independent speech recognition systems have poor accuracy not exceeding 75%.In this paper we describe a two-module speaker independent speech recognition system for all-British English speech. The first module performs phoneme recognition using two-level neural networks. The second module executes word recognition from the string of phonemes employing Hidden Markov Model. The system was trained by British English speech consisting of 2000 words uttered by 100 speakers. The test samples comprised 1000 words spoken by a different set of 50 speakers. The recognition accuracy is found to be 92% which is well above the previous results.

  • Speaker independent speech recognition
  • neural network
  • hidden Markov model
  • phonemes

For citation

Maheswari N. Uma, Kabilan A.P., Venkatesh R. Speaker Independent Speech Recognition System Using Neural Networks // Journal of Radio Electronics. – 2009. – No. 7.

References

  1. Medser L. R. and Jain L. C., Recurrent Neural Network: Design and Applications. London, New York: CRC Press LLC,2001.
  2. D.A.Reynolds,An Overview of Automatic Speaker Recognition Technology, Proc. ICASSP 2002, Orlando, Florida, pp. 300-304.
  3. Philip D. Wasserman, Advanced methods in neural computing, Von Nostrand Renhold,1993
  4. D.F. Specht, Probabilistic neural networks,Neural Networks, vol.3,pp. 109-118,1990.
  5. R.O.Duda, P.E. Hart, and D.G.Stork, pattern classification, John Wiley and sons,second edition,2001.
  6. L.Deng and D.OShaughnessy, Speech processing: a dyanamic and optimization-oriented approach, Marcel Dekker Inc.,2003
  7. R.Kronland-Martinet, J.Morlet and A.Grossman, Analysis of sound patterns through wavelet transformation, International Journal of Pattern Recognition and Artificial Intelligence, Vol.1(2)
  8. John Coleman, Introducing speech and language processing, Cambridge university press,2005
  9. L.Mesbahi and A.Benyetto,Continuous speech recognition by adaptive temporal radial basis function, in IEEE international conference on systems,Man and Cybernetics,2004,pp.574-579
  10. H. Sakoe and S. Chiba, Dynamic programming optimization for spokenword recognition, Proceedings of ICASSP-78, vol. 26, no. 1, pp. 43-49, 1997.
  11. Timit acoustic-phonetic continuous speech corpus, National Institute of Standards and Technology speech Disc 1-1.1, October 1990.
  12. Bourlard, H., Kamp, Y., Ney, H., and Wellekens, C. J. "Speaker-Dependent Connected Speech Recognition Via Dynamic Programming and Statistical Methods," in Speech and Speaker Recognition, ed. M. R. Schroeder, Basel, Switzerland: Karger, pp. 115-148,1985.
  13. F. Jelinek,Statistical Methods for Speech Recognition, The MIT Press, 1998.
  14. L. R. Rabiner, B. H. Juang, Fundamentals of Speech Recognition, Prentice Hall, Englewood Cliffs, New Jersey, 1993.
  15. E. Harborg, Hidden Markov Models Applied to Automatic Speech Recognition, PhD Thesis, Norwegian Institute of Technology, Trondheim, Aug. 1990.
  16. Abbas Ahmadi,Fakhri Karray,Mohamed Kamel,Modular-based classifier for phoneme recognition,IEEE International Symposium on Signal Processing and Information Technology,2006
  17. F. Karray and C. de Silva, Soft computing and intelligent systems design: Theory, Tools and Applications, Addison Wesley Publishing