Classical Tamil Speech Enhancement with Modified Threshold Function using Wavelets

  • Indra., J (Department of Electronics and Instrumentation Engineering, Kongu Engineering College) ;
  • Kasthuri., N (Department of Electronics and Instrumentation Engineering, Kongu Engineering College) ;
  • Navaneetha Krishnan., S (Department of Electronics and Instrumentation Engineering, Kongu Engineering College)
  • Received : 2015.04.22
  • Accepted : 2016.06.28
  • Published : 2016.11.01


Speech enhancement is a challenging problem due to the diversity of noise sources and their effects in different applications. The goal of speech enhancement is to improve the quality and intelligibility of speech by reducing noise. Many research works in speech enhancement have been accomplished in English and other European Languages. There has been limited or no such works or efforts in the past in the context of Tamil speech enhancement in the literature. The aim of the proposed method is to reduce the background noise present in the Tamil speech signal by using wavelets. New modified thresholding function is introduced. The proposed method is evaluated on several speakers and under various noise conditions including White Gaussian noise, Babble noise and Car noise. The Signal to Noise Ratio (SNR), Mean Square Error (MSE) and Mean Opinion Score (MOS) results show that the proposed thresholding function improves the speech enhancement compared to the conventional hard and soft thresholding methods.


  1. RichaTyagi, SunitaMaithani, "A Hybrid Speech Enhancement System Based On Wavelet Denoising", in Proceedings of 13th Oriental COCOSDA Workshop, 2010.
  2. Sachin Singh, Manoj Tripathya & R. S. Ananda, "Subjective and Objective Analysis of Speech Enhancement Algorithms for Single Channel Speech Patterns of Indian and English Languages", IETE Technical Review, Vol. 31, No. 1, 2014
  3. J.R. Deller, J.H.L. Hansen, J.G. Proakis, Discrete-Time Processing of Speech Signals, Second ed. IEEE Press. 2000.
  4. S.F. Boll, "Suppression of acoustic noise in speech using spectral subtraction", IEEE Trans. Acoust. Speech Signal Process. ASSP-27, pp. 113-120, 1979.
  5. M. Berouti, R. Schwartz, J. Makhoul, "Enhancement of speech corrupted by acoustic noise", in Proc. IEEE Internat. Conf. on Acoust. Speech Signal Process. (ICASSP), Washington DC, pp. 208-211, 1979.
  6. S. Kamath, P. Loizou, "A multi-band spectral subtraction method for enhancing speech corrupted by colored noise", in Proc. IEEE Internat. Conf. Acoust. Speech Signal Process. (ICASSP), Orlando, Florida, 2002.
  7. Y. Ghanbari, M. Karami, "Spectral subtraction in the wavelet domain for speech enhancement", Internat. J. Software Inf. Technol. (IJSIT) 1 (1), pp. 26-30, 2004.
  8. Y. Ghanbari, M. Karami, B. Amelifard, "Improved multiband spectral subtraction method for speech enhancement", in Proc. 6th IASTED Internat. Conf. on Signal Image Process. USA, pp. 225-230, 2004.
  9. H. Sameti, H. Sheikhzadeh, Deng, Li, R.L. Brennan, "HMM-based strategies for enhancement of speech signals embedded in nonstationary noise", IEEE Trans. Speech AudioProcess. 6 (5), pp. 445-455, 1998.
  10. M. Klein, P. Kabal, "Signal subspace speech enhancement with perceptual post-filtering" in Proc. IEEE Internat. Conf. Acoust. Speech Signal Process. (ICASSP) 1, pp. 537-540, 2002.
  11. H. Sheikhzadeh, H. R. Abutalebi, "An improved wavelet based speech enhancement system", in Proc. 7th Eur. Conf. Speech Comm. Technol. (Euro Speech), Aalborg, Denmark, September 2001.
  12. J. Seok, K. Bae, "Speech enhancement with reduction of noise components in the wavelet domain", in Proc. IEEE Internat. Conf. Acoust. Speech Signal Process. (ICASSP) 2, pp. 1323-1326, 1997.
  13. J. Indra, N. Kasthuri, "Development of Noisy Corpus Database for Classical Tamil Language", International Journal of Applied Engineering Research, 2014, Vol. 9, no. 23, pp. 23039-23048, 2014
  14. K. Prahallad, E. Naresh Kumar, V. Keri, S. Rajendran and A. W Black., "The IIIT-H Indic Speech Databases," in Proceedings of Inter speech, Portland, 2012. OR. Available:
  15. Noise signals is referred from Columbia University-Newyork
  16. D. L. Donoho and I. M. Johnstone," Ideal spatial adaptation by wavelet shrinkage," Biometrica, vol. 81, no. 3, pp. 425-455, 1994.
  17. D. L. Donoho, "De-noising by soft thresholding," IEEE Trans. Inform. Theory, vol. 41, pp. 613-627, May 1995.
  18. D. M. Ballesteros, "Procesamiento digital de senalesutilizando Matlab y Simulink. Chapter: Transformada Wavelet Discreta". Ed. Orcas, pp. 61-83, 2010.
  19. D. L. Donoho, I. M. Johnstone, "Threshold selection for wavelet shrinkage of noisy data", 16th Annual International Conference of the IEEE, pp. A24-A25, 1994.
  20. I. M. Johnston, B. W. Silverman, "Wavelet threshold estimators for data with correlated noise", J. Roy. Statist. Soc. Ser. B 59, pp. 319-351, 1997.
  21. V. Turbin, N. Faucheur, "Estimation of speech quality of noise reduced signals", in Proceedings of Online workshop meas. speech audio quality network, 2007.
  22. Bernhard Wieland, thesis (October 2009) "Speech Signal Noise Reduction with Wavelets", pp. 55-56
  23. ITU-T. P. 835. "Series P: Telephone transmission quality, telephone installations, local line networks: methods for objective and subjective assessment of quality", 2003.