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

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.

[1]  James R. Glass,et al.  Historical Development and Future Directions in Speech Recognition and Understanding , 2007 .

[2]  S. R. Mahadeva Prasanna,et al.  Temporal and Spectral Processing Methods for Processing of Degraded Speech: A Review , 2009 .

[3]  Komal R. Borisagar,et al.  Simulation and Comparative Analysis of LMS and RLS Algorithms Using Real Time Speech Input Signal , 2010 .

[4]  Michael T. Johnson,et al.  Speech signal enhancement through adaptive wavelet thresholding , 2007, Speech Commun..

[5]  Mojtaba Lotfizad,et al.  A Family of Adaptive Filter Algorithms in Noise Cancellation for Speech Enhancement , 2011, ArXiv.

[6]  Manjusha N. Chavan,et al.  Studies on Implementation of Wavelet for Denoising Speech Signal , 2010 .

[7]  Jérôme Boudy,et al.  Experiments with a nonlinear spectral subtractor (NSS), Hidden Markov models and the projection, for robust speech recognition in cars , 1991, Speech Commun..

[8]  P. Devi Pradeep,et al.  NOISE SUPPRESSION IN SPEECH SIGNALS USING ADAPTIVE ALGORITHMS , 2010 .

[9]  Radha..  Optimal Adaptive Filtering Technique for Tamil Speech Enhancement , 2012 .

[10]  A. M. Natarajan,et al.  Word and triphone based approaches in continuous speech recognition for Tamil language , 2008 .

[11]  Palden Lama,et al.  Speech Recognition with Dynamic Time Warping using MATLAB , 2010 .

[12]  Shashikant L. Sahare,et al.  Different Approaches of Spectral Subtraction method for Enhancing the Speech Signal in Noisy Environments , 2011 .