Total views : 346

A Novel Framework for Speech Signal Denoising using PSO Optimized ICA-DWT Algorithm


  • Department of Electronics and Communication Engineering, Vivekananda Institute of Technology, Kumbalagodu,Kengeri, Bengaluru – 560074, Karnataka, India
  • Department of Electronics and Communication Engineering, SJB Institute of Technology, No.67, BGS Health and Education City, Dr. Vishnuvardhan Road, Kengeri, India


Objectives: In this paper a hybrid approach of ICA-DWT algorithm optimized using Particle Swarm Optimization (PSO) is proposed to deal with problems of aperiodic and period noises in industrial noise environment. Method/analysis: The feature of Independent Component Analysis (ICA) for separating the signals of various channels is exploited to separate noise peaks from the speech channel. To reserve the original signal and discern the noise, the speech is segmented in various levels of frequencies via discrete wavelet transform. The adaptive filtration through wavelet filters has been a powerful tool for signal segmentation into various frequencies. The output of ICA is sourced to Discrete Wavelet Transform (DWT) and is optimized using PSO to generate threshold value and number of wavelets for it. Findings: The results indicate that additional overhead computation of DWT has a better Signal-to-Noise Ratio (SNR) value compared to clean fast ICA algorithm and thus validate the improvement in speech signal intelligibility and quality.For the range of input signals and noise environment, the optimization of PSO to filter the speech signals has best SNR compared to conventional algorithm. Novelty/ Improvement: In the proposed denoising model two stages optimized filtering is presented. The number of wavelet levels and value of threshold is depicted using objective function to minimize Spectral Noise Density (SND). The objective function is optimized with PSO in constraints of SND to generate the best possible levels of DWT and thus maximize the SNR ultimately.


DWT, ICA, PSO, Speech Signals.

Full Text:

 |  (PDF views: 332)


  • Choi J, Yeom J, Chang A, Byun Y, Kim Y. Hybrid pansharpening algorithm for high spatial resolution satellite imagery to improve spatial quality. Geoscience and Remote Sensing Letters. 2013; 10(3):490–4.
  • Roman N, Woodruff J. Speech intelligibility in reverberation with ideal binary masking: Effects of early reflections and SNR threshold. The Journal of the Acoustical Society of America. 2013; 133(3):1707–17.
  • Zhou T. SNR. In Signal-to-Noise Ratio, Werner Dubitzky et al., editors. Springer New York; 2013. p. 1939–40.
  • Ljung R, Israelsson K, Hygge S. Speech intelligibility and recall of spoken material heard at different SNRs and the role played by working memory capacity. In Applied Cognitive Psychology. 2013; 27(2):198–203.
  • Balcan DC, Rosca J. For speech enhancement with missing TF content. Lecture Notes in Computer Science, Springer Berlin Heidelberg. 2006; 3889:552–60.
  • Hong L, Rosca J, Balan R. based single channel speech enhancement using wiener filter, Institute of Electrical and Electronics Engineers (IEEE) Symposium on Signal Processing and Information Technology (ISSPIT); 2003. p.522–5.
  • Balakrishnalavu, Potnuru VA. Speech enhancement using constrained-ICA with Bessel features [Degree of Master of Science in Electrical Engineering thesis]. Sweden, Blekinge Institute of Technology; 2011 Jan.
  • Rutkowski T, Cichocki A, Barros AK. Speech enhancement using adaptive filters and approach. In the Proceedings of International Conference on Artificial Intelligence in Science And Technology (AISAT); 2000. p. 191–6.
  • Hong L, Rosca J, Balan R. Bayesian single channel speech enhancement exploiting sparseness in the ICA domain, In the 12th European Signal Processing Conference; 2004. p.1713–16.
  • Mihov SG, Ivanov RM, Popov AN. Denoising speech signals by wavelet transform. Annual Journal of Electronics.2009:712–5.
  • Chavan MS, Chavan MMN, Gaikwad MS. Studies on implementation of wavelet for denoising speech signal. International Journal of Computer Applications. 2010; 3(2):1–7.
  • Tomic M, Sersic D. Point-wise adaptive wavelet transform for signal denoising. Informatica. 2013; 24(4):637–56.
  • Sardy S, Tseng P, Bruce A. Robust wavelet denoising.Institute of Electrical and Electronics Engineers (IEEE) Transactions on signal processing. 2009; 49(6):1146–52.
  • Attias H, Deng L, Acero A, Platt JC. A new method for speech denoising and robust speech recognition using probabilistic models for clean speech and for noise.Proceeding Eurospeech. 2001 Sep; 3:1903–6.
  • Langlois D, Chartier S, Gosselin D. An introduction to independent component analysis: InfoMax and FastICA algorithms. Tutorials in Quantitative Methods for Psychology. 2010; 6(1):31–8.
  • Bijalwan A, Goyal A, Sethi N. Wavelet transform based image denoise using threshold approaches. International Journal of Engineering and Advanced Technology. 2012; 1(5):218–21.
  • Kennedy J, Eberhart RC. A discrete binary version of the particle swarm algorithm. In proceedings of Institute of Electrical and Electronics Engineers (IEEE) International Conference on Computational Cybernetics and Simulation.1997 Oct; 5:4104–8.
  • Lakshmikanth S, Natraj KR, Rekha KR. A hybrid approach for speech signal denoising using ICA-DWT. International Journal of Electronics Communication and Computer Engineering. 2014; 5(6):1395–9.
  • Lakshmikanth S, Natraj KR, Rekha KR. Novel algorithm for noise cancellation in speech using ICA-EMD using PSO. International Journal of Signal Processing, Image Processing and Pattern Recognition. 2014; 7(6):345–58.
  • Lakshmikanth S. Novel approach for noise cancellation in industrial environment [Ph.D. thesis]. Department of Electronics Engineering, Jain University, Karnataka, India; 2015.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.