Speech is produced when air from the lungs passes through the throat, the vocal cords, the mouth and the nasal tract. Speech processing is the study of the speech signals and the processing methods of these signals. Speech enhancement is a technique used to reduce the background noise present in the speech signal. It simply means the improvement in intelligibility and quality of degraded speech. The need to enhance speech signal arises in many situations in which the speech signal originates from noisy locations. The aim of the proposed method is to reduce the background noise present in the Tamil speech signal by using spectral subtraction and adaptive techniques. There has been no such works or efforts in the past in the context of Tamil speech enhancement in the literatures. Fifty Tamil speeches are taken as sample speech from the Tamil database [1] [2]. Sample noises such as pink noise, white noise and Volvo noise are taken. By using the spectral subtraction techniques such as Non-Linear, Multiband and Minimum Mean Square Error spectral subtraction and adaptive techniques such as Least Mean Square and Recursive Least Square methods, enhanced Tamil speech is obtained. Performance of the above two techniques are compared based on their Signal to Noise Ratio and Log Spectral Distance.

1. M. Selvam, A. M. Natarajan, R. Thangarajan, "Structural parsing of natural language text in Tamil Language using dependency model ", International Journal of Computer Processing of Languages, Volume 22, Issue 3, Page No:237-256, 2009.
2. R. Thangarajan, A. M. Natarajan, M. Selvam, "Development of Large Vocabulary Speech Corpus for Tamil Language", International conference on "Emerging technologies in Intelligent system and Control", Volume 2,2005.
3. S. Boll, "Suppression of Acoustic Noise in Speech Using Spectral Subtraction" IEEE Transactions on Acoustics, Speech,Signal processing, Volume 27, Issue 2, Page No: 113-120, 1979.
4. Brady N. M. Laska, MiodragBolic and Rafik A. Goubran , "Particle Filter Enhancement of Speech Spectral Amplitudes", IEEE Transactions on audio, speech, and language processing, Volume 18, Issue 8, Page No:2155-2167, 2010.
5. M. Berouti, R. Schwartz and J Makhoul,"Enhancement of Speech corrupted by acoustic noise", in Proceedings of IEEE International Conference on Acoustics, Speech and Signal processing , Volume 4, Page No: 208–211, 1979.
6. Krishnamoorthy. P and MahadevaPrasanna. S. R ," Temporal and spectral processing Methods for Processing of Degraded Speech: A Review", IETE technical review, Vol-26, Issue-2, Page No:137-148, 2009.
7. NavneetUpadhyay and AbhijitKarmakar, "The spectral subtractive-type algorithms for enhancing speech in noisy environments", in Proceedings of International Conferenc on Recent Advances in Information Technology, ISM Dhanbad, India, Page No: 841- 847,2012.
8. Paurav Goel1, Anil Garg, "Developments in Spectral Subtraction for Speech Enhancement", International Journal of Engineering Research and Applications (IJERA), Volume 2, Issue 1, Page No: 55 to 63, 2012.
9. Anuradha R. Fukane, Shashikant L. Sahare "Different approaches of spectral subtraction method for enhancing speech signal in noisy environments", International Journal of Scientific and Engineering Research, Volume 2, Issue 5, 2011.
10. S. Kamath and P. Loizou, "A multiband spectral subtraction method for enhancing speech corrupted by colored noise", 'IEEE International Conference on Acoustics, Speech and Signal processing, 2002
11. Y. Eprahim and D. Malah (2002), "Speech Enhancement using minimum mean- square error short- time spectral amplitude estimator",'IEEE Transactions on on Acoustics,Speech,and Signal processing, Volume 32, No:6, Page No:328–337, 1984.
12. R. Martin "Speech Enhancement using MMSE short Time Spectral Estimation with Gamma Distributed Speech Priors", IEEE International Conference on Acoustics, Speech,and Signal processing , Volume 1,Page No: 253–256, 2002.
13. Gang Wang, Chunguang Li, and Le Dong, "Noise Estimation Using Mean Square Cross Prediction Error for Speech Enhancement", IEEE transactions on circuits and systems, Volume 57, Issue 7, Page No: 1489-1499, 2010.
14. C. Breithaupt and R. Martin,"Analysis of the Decision-Directed SNR Estimator for Speech Enhancement with respect to Low-SNR and Transient Conditions", IEEE transactions on audio, speech, and language processing, Volume 19, Issue 2, Page No:277-289, 2011.
15. Jie Wang, Hao Liu, ChengshiZheng, Xiaodong Li " Spectral subtraction based on two-stage spectral estimation and modified cepstrum thresholding", Applied Acoustics, Volume 74, Issue 3, Page No: 450–458, 2013.
16. John Hakon husoy, "Adaptive filters viewed as iterative linear equation solvers" Third International conference on "Numerical Analysis and Applications", 2004.
17. B. Widrow, J. R. Glover, J. M. McCool, J. Kaunitz, C. S. Williams, R. H. Hearn, J. R. Zeidler,Eugene Dong, R. C. Goodlin: "Adaptive NoiseCancelling: Principles and Applications", Proceedings of the IEEE, Volume 63, Issue 12, Page No: 1692, 1716, 1975.
18. Tekale P. B , 2 Kulkarni S. R, " Modified Kalman Based NLMS Algorithm For Noise Cancellation", International journal of Systems and Technologies, Volume 5 , Issue 1,Page No: 47-55,2012.
19. Harjeet Kaur, Dr. Rahul Malhotra, Anjali Patki,"Performance Analysis of Gradient Adaptive LMS Algorithm", International Journal of Scientific and Research Publications, Volume 2, Issue 1, Page No: 1-4, 2012.
20. Jasveen Kaur and RanjitKaur, "A Comparison Study of Power Spectrum Densities of Various Adaptive Algorithm Using Adaptive Filter", International Journal of Engineering Research and Applications (IJERA), Volume 2, Issue 3, Page No:2335-2341, 2012.
21. Vimala C, Radha V, "optimal Adaptive filtering for Tamil Speech Enhancement", International Journal of Computer Applications, Volume 41, Issue 17, 2012.
22. S. Ogata, T. Shimamura , "Reinforced Spectral Subtraction method to enhance speech signal" , IEEE International Conference on Electrical and Electronic Technology, Volume 1, Page No:242-245, 2001.

Mbss Mmse Rls Lms Snr Lsd