Abstract

The main goal of Speech enhancement is to enhance the performance of speech communication systems in noisy environments. The problem of enhancing speech which is corrupted by noise is very large, although a lot of techniques have been introduced by the researchers over the past years. This problem is more severe when there is no additional information on the nature of noise degradation is available in which case the enhancement technique must utilize only the specific properties of the speech and noise signals. Signal representation and enhancement in cosine transformation is observed to provide significant results. Discrete Cosine Transformation has been widely used for speech enhancement. In this research study, instead of DCT, a hybrid technique called DCTSLT which is the combination of Discrete Cosine Transform (DCT) and Slantlet Transform (SLT) is proposed for continuous energy compaction along with critical sampling and flexible window switching. In order to deal with the issue of frame to frame deviations of the Cosine Transformations, the proposed transform is combined with Time Domain Pitch Synchronous Overlap-Add (TD-PSOLA) method. Moreover, in order to improve the performance of noise reduction of the system, a Hybrid Vector Wiener Filter approach (HVWF) is used in this study. Experimental result shows that the proposed system performs well in enhancing the speech as compared with other techniques.

Keywords:

Discrete cosine transform, slantlet transform, speech enhancement, time domain pitch synchronous overlap-ad method,

References

1. Abd El-Fattah, M.A., M.I. Dessouky, S.M. Diab and F.E. Abd El-Samie, 2008. Adaptive wiener filtering approach for speech enhancement. Prog. Electromagn. Res., 4: 167-184.
   CrossRef    
2. Abdelkader, C. and C. Adnan, 2010. Implementation of the Arabic speech synthesis with TD-PSOLA modifier. Int. J. Signal Syst. Control Eng. Appl., 3(4): 77-80.
   CrossRef    
3. Balaji, V.R. and S. Subramanian, 2014. A novel speech enhancement approach based on modified DCT and improved pitch synchronous analysis. Am. J. Appl. Sci., 11(1): 24-37.
   CrossRef    
4. Berouti, M., R. Schwartz and J. Makhoul, 1979. Enhancement of speech corrupted by acoustic noise. Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '79), pp: 208-211.
   CrossRef    
5. Boll, S.F., 1979. Suppression of acoustic noise in speech using spectral subtraction. IEEE T. Acoust. Speech, 27(2): 113-120.
   CrossRef    
6. Chang, J.H., 2005. Warped discrete cosine transform-based noisy speech enhancement. IEEE T. Circuits-II, 52(9): 535-539.
   
7. Cheveigne, A. and H. Ahara, 1998. A comparative evaluation of Fo estimation algorithm. Proceedings of the Euro Speech Conference (ESC'98). Norvege, pp: 453-467.
   PMid:9514016    
8. Ding, H. and I.Y. Soon, 2009. An adaptive time-shift analysis for DCT based speech enhancement. Proceeding of 7th International Conference on Information, Communications and Signal Processing (ICICSP, 2009), pp: 1-4.
   CrossRef    
9. Ephraim, Y. and D. Malah, 1984. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE T. Acoust. Speech, 32(6): 1109-1121.
   CrossRef    
10. Ephraim, Y. and H.L. Van Trees, 1993. A signal subspace approach for speech enhancement. IEEE T. Speech Audi. P., 3(4): 251-266.
    CrossRef    
11. Ephraim, Y. and H.L. Van Trees, 1995. A spectrally based signal subspace approaches for speech enhancement. Proceeding of International Conference on Acoustics, Speech and Signal Processing (ICASSP, 1995), pp: 804-807.
    
12. Faizal, M.A., H.B. Rahmalan, E.H. Rachmawanto and C.A. Sari, 2012. Impact analysis for securing image data using hybrid SLT and DCT. Int. J. Future Comput. Commun., 1(3): 308-311.
    CrossRef    
13. Hardie, R.C., K.J. Barnard and E.E. Armstrong, 1997. Joint MAP registration and high-resolution image estimation using a sequence of undersampled images. IEEE T. Image Process., 6(12): 1621-1633.
    CrossRef    PMid:18285233    
14. Jung, S.I., Y.G. Kwon and S.I. Yang, 2006. Speech enhancement by wavelet packet transform with best fitting regression line in various noise environments. Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP, 2006), pp: 01.
    
15. Kim, S.P. and W.Y. Su, 1991. Recursive high-resolution reconstruction of blurred multiframe images. Proceeding of International Conference on Acoustics, Speech and Signal Processing (ICASSP, 1991), pp: 2977-2980.
    CrossRef    
16. Kumar, S. and S.K. Mutto, 2009. Distortion data hiding based on slantlet transform. Proceedings of the 2009 International Conference on Multimedia Information Networking and Security (MINES '09), pp: 48-52.
    CrossRef    
17. Maitra, M., A. Chatterjee and F. Matsuno, 2008. A novel scheme for feature extraction and classification of magnetic resonance brain images based on slantlet transform and support vector machine. Proceedings of the SICE Annual Confference, pp: 1130-1134.
    CrossRef    
18. Martin, R., 2001. Noise power spectral density estimation based on optimal smoothing and minimum statistics. IEEE T. Speech Audi. P., 9(5): 504-512.
    CrossRef    
19. Michaeli, T. and Y.C. Eldar, year. A hybrid vector wiener filter approach to translational super-resolution. IEEE T. Image Process.
    
20. Muralishankar, R., A.G. Ramakrishnan and P. Prathibha, 2004. Modification of pitch sing DCT in the source domain. Speech Commun., 42(2): 143-154.
    CrossRef    
21. Nar, V.V., A.N. Cheeran and S. Banerjee, 2013. Verification of TD-PSOLA for implementing voice modification. Res. Appl., 3(3): 461-465.
    
22. Rabiner, L., M. Cheng, A. Rosenberg and C. McGonegal, 1976. A comparative performance study of several pitch detection algorithms. IEEE T. Acoust Speech, 24(5): 399-418.
    CrossRef    
23. Rao, V.R., R. Murthy and K.S. Rao, 2011. Speech enhancement using cross-correlation compensated multi-band wiener filter combined with harmonic regeneration. J. Signal Inform. Process., 2: 117-124.
    CrossRef    
24. Scalart, P and J.V. Filho, 1996. Speech enhancement based on a priori signal to noise estimation. Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP, 1996), pp: 629-632.
    CrossRef    
25. Shuwang, C., A. Tao and H. Litao, 2009. Discrete cosine transform image compression based on genetic algotithm. Proceeding of International Conference on Information Engineering and Computer Science (ICIECS, 2009), pp: 1-3.
    
26. Yehia, H., P. Rubin and E. Vatikiotis-Bateson, 1998. Quantitative association of vocal-tract and facial behaviour. Speech Commun., 26(1): 23-43.
    CrossRef    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.