Efficient Speaker Independent Isolated Speech Recognition for Tamil Language Using Wavelet Denoising and Hidden Markov Model

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 222)


Current research on Automatic Speech Recognition (ASR) focuses on developing systems that would be much more robust against variability in environment, utterance, speaker and language. In this paper all these major factors are considered to develop a system which works powerfully for recognizing a set of Tamil spoken words from a group of people at different noisy conditions. Developing an ASR system in the presence of noise critically affects the speech quality, intelligibility, and recognition rate of the system. Thus, to make a system robust against different noisy conditions, the most popular speech enhancement techniques such as spectral subtraction, adaptive filters and wavelet denoising are implemented at four SNR dB levels namely −10, −5, 5 and 10 with three types of noise such as white, pink and babble noise. This research work is carried out for developing a speaker independent isolated speech recognition system for Tamil language using Hidden Markov Model (HMM) under the above noise conditions. Better improvements are obtained when the proposed system is combined with speech enhancement preprocessor. Based on the experiments 88, 84 and 96 % of recognition accuracy are obtained from enhanced speech using Nonlinear Spectral Subtraction, RLS adaptive Filter and Wavelet approach respectively.


Nonlinear spectral subtraction RLS adaptive algorithm Wavelet denoising MFCC HMM Tamil speech recognition 


  1. 1.
    Baker JM, Deng L, Khudanpur S, Lee C-H, Glass J, Morgan N (2006–2007) Historical development and future directions in speech recognition and understanding. MINDS. Report of the speech understanding working groupGoogle Scholar
  2. 2.
    Krishnamoorthy P, Mahadeva Prasanna SR (2009) Temporal and spectral processing methods for processing of degraded speech: a review. IETE Tech Rev 26(2):137–148Google Scholar
  3. 3.
    Fukane AR, Sahare SL (2011) Different approaches of spectral subtraction method for enhancing the speech signal in noisy environments. Int J Sci Eng Res 2(5). ISSN 2229-5518Google Scholar
  4. 4.
    Goel1 P, Garg A (2012) Developments in spectral subtraction for speech enhancement. Int J Eng Res Appl (IJERA). 2(1):055–063. ISSN: 2248-9622Google Scholar
  5. 5.
    Vimala C, Radha V (2012) A family of spectral subtraction algorithms for tamil speech enhancement. Int J Soft Comput Eng (IJSCE) 2(1). ISSN: 2231-2307Google Scholar
  6. 6.
    Lockwood P, Boudy J (1992) Experiments with a nonlinear spectral subtractor (NSS) hidden markov models and the projection for robust speech recognition in cars. Speech Commun 11(2–3):215–228Google Scholar
  7. 7.
    JaganNaveen V, Prabakar T, Venkata Suman J, Devi Pradeep P (2010) Noise suppression in speech signals using adaptive algorithms. Int J Signal Process Image Process Pattern Recogn 3(3):87–96Google Scholar
  8. 8.
    Hadei SA, Student member IEEE, Lotfizad M (2010) A family of adaptive filter algorithms in noise cancellation for speech enhancement. Int J Comput Electr Eng 2(2):1793–8163Google Scholar
  9. 9.
    Borisagar KR, Kulkarni GR (2010) Simulation and comparative analysis of LMS and RLS algorithms using real time speech input signal. Global J Res Eng 10(5):44 (Ver1.0)Google Scholar
  10. 10.
    Vimala C, Radha V (2012) Optimal adaptive filtering technique for tamil speech enhancement. Int J Comput Appl (0975–8887) 41(17):23–29Google Scholar
  11. 11.
    Chavan MS, Chavan MN, Gaikwad MS (2010) Studies on implementation of wavelet for denoising speech signal. Int J Comput Appl (0975–8887) 3(2):1–7Google Scholar
  12. 12.
    Johnson MT, Yuan X, Ren Y (2007) Speech signal enhancement through adaptive wavelet thresholding. Speech Commun 49(2):123–133Google Scholar
  13. 13.
    Lama P, Namburu M (2010) Speech recognition with dynamic time warping using MATLAB. CS 525, SPRING 2010—Project reportGoogle Scholar
  14. 14.
    Thangarajan R, Natarajan AM, Selvam M (2008) Word and triphone based approaches in continuous speech recognition for tamil language. WSEAS Trans Signal Process 4(3). ISSN: 1790-5022Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.Department of Computer ScienceAvinashilingam Institute for Home Science and Higher Education for WomenCoimbatoreIndia

Personalised recommendations