A Novel Block De-Noising Algorithm for Sounds of Indian Musical Instruments with Modified Threshold in Wavelet Domain

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 221)


The problem of estimating the musical instrument sound signal, corrupted by additive white Gaussian noise has been of interest to many researchers for practical as well as theoretical reasons. The removal of white Gaussian noise is difficult as it persists at all the frequencies in the signal. Many of the methods, especially those based on wavelet technique have become popular, due to the number of advantages over the traditional methods. It has been shown that wavelet based thresholding is simple and optimal solution, also guarantees better rate of convergence. In this paper, a novel DWT based algorithm using block de-noising along with modified threshold is proposed. For experimental purpose, the sound signals of shehnai, dafli and flute are taken. The signal is first divided into the multiple blocks of samples and then both hard and soft thresholding methods are used on each block. All the blocks obtained after individual block de-noising are concatenated to get the final de-noised signal. When the sound signal corrupted with variable percentage of Gaussian noise, passed through this algorithm; significant improvement in PSNR is observed over normal wavelet thresholding method. The quality of sound signal obtained through this algorithm is perceptually close to original signal.


Block denoising Gaussian noise Wavelet thresholding Wavelet coefficients 


  1. 1.
    Sharma R, Pyara VP (2012) A novel approach to synthesize sounds of some Indian musical instruments using DWT. Int J Comput Appl 45(13):19–22Google Scholar
  2. 2.
    Sharma R, Pyara VP (2012) A comparative analysis of mean square error adaptive filter algorithms for generation of modified scaling and wavelet function. Int J Eng Sci Technol 4(4):1396–1401Google Scholar
  3. 3.
    Donoho DL (1993) Unconditional bases are optimal bases for data and for statistical estimation. Appl Comput Harmonic Anal 1:100–115MathSciNetMATHCrossRefGoogle Scholar
  4. 4.
    Donoho DL, Johnstone IM (1995) Adapting to unknown smoothness via wavelet shrinkage. J Am Stat Assoc 90:1200–1224MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Donoho DL, Johnstone IM, Kerkyacharian G, Picard D (1995) Wavelet shrinkage: asymptopia. J Roy Stat Soc 57(2):301–369MathSciNetMATHGoogle Scholar
  6. 6.
    Cho N, Kuo CJ (2010) Sparse representation of musical signals using source-specific dictionaries. IEEE Trans, 3rd edn. Academic PressGoogle Scholar
  7. 7.
    Serrano EP (2002) Fabio.: application of the wavelet transform to acoustic emission signals processing. IEEE Sig Process Lett 17(11):913–916Google Scholar
  8. 8.
    Pan P, Zhang L, Dai G, Zhang H (1999) Two denoising methods by wavelet transform. IEEE Trans Sig Process 47(12):3401–3406MATHCrossRefGoogle Scholar
  9. 9.
    Aggarwal R et al (2011) Noise reduction of speech signal using wavelet transform with modified universal threshold. IJCA 20(5):14–19CrossRefGoogle Scholar
  10. 10.
    Balakrishnan V, Borges N, Parchment L (2008) Wavelet denoising and speech enhancement. IEEE Conf Image Process 1–5Google Scholar
  11. 11.
    Gultekin O, Erer I, Kaplan M (2009) Empirical mode decomposition based de-noising for high resolution direction of arrival estimation. EUSIPCO 1983–1986Google Scholar
  12. 12.
    Chen Y (2009) Realization of wavelet soft threshold de-noising technology based on visual instrument. IEEE Int Jt Conf Artif Intell 849–852Google Scholar
  13. 13.
    Chang SG, Yu B, Vetterli M (2000) Adaptive wavelet thresholding for image denoising and compression. IEEE Trans Image Process 9:1532–1546MathSciNetCrossRefGoogle Scholar
  14. 14.
    Berger J, Coifman RR, Maxim JG (1994) Removing noise from music using local trigonometric bases and wavelet packets. J Audio Eng Soc 42(10):808–818Google Scholar
  15. 15.
    Johnson MT, Yuan X, Ren Y (2007) Speech signal enhancement through adaptive wavelet thresholding. Speech Commun 49(10):123–133CrossRefGoogle Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.Department of Electrical EngineeringDayalbagh Educational InstituteAgraIndia

Personalised recommendations