The week's pick
Reseach Article
A Hybrid HMM/SVM Classifier for Wavelet Front End Robust Automatic Speech Recognition
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 75 - Number 16 |
| Year of Publication: 2013 |
| Authors: Rajeswari, N. N. S. S. R. K. Prasad, Sathyanarayana V |
10.5120/13194-0856
|
Rajeswari, N. N. S. S. R. K. Prasad, Sathyanarayana V . A Hybrid HMM/SVM Classifier for Wavelet Front End Robust Automatic Speech Recognition. International Journal of Computer Applications. 75, 16 ( August 2013), 17-22. DOI=10.5120/13194-0856
Abstract
Noisy ambient conditions pose a challenge to speech recognition, increasing the acoustic confusability, thereby looking for powerful acoustic models to improve the generalization ability of the machine learning and improve the recognition accuracy. This paper discusses a hybrid classifier that harness the power of hidden markov models (HMM) and the discriminative support vector machines (SVM) applied to a wavelet front end based automatic speech recognition (ASR) system. The experiments are performed on speaker independent TIMIT database which are trained in a clean environment and later tested in the presence of additive white gaussian noise (AWGN) for various SNR levels using the HTK toolkit, SVMLib and SVMLight software tool. Experiments indicate that for large vocabulary the classification power of SVMs and the elegant iterative training algorithms for the estimation of HMMs together as a hybrid classifier with the wavelet front end performs better than the conventional classifiers.
References
- Deng, L. , Redmond, W. A. , Li, X. , 2013. Machine Learning Paradigms for Speech Recognition: An Overview. In IEEE Transactions on Audio, Signal and Language Processing, 1060-1089.
- Rabiner, L. and Juang, B. H. 1993. Fundamentals of Speech Recognition, Prentice Hall.
- Young, S. 2009. The HTK Book. Version 3. 4, Cambridge University Engineering Department. Cambridge, UK.
- Rabiner, L. R. 1989. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. In Proceedings of the IEEE, 257-286.
- Jiang, H. , Li, X. , Liu, C. 2006. Large Margin HMMs for Speech Recognition. In IEEE Transactions on Speech and Audio Language Processing, 14, 1584-1595.
- Hoon, C. and Lee, S. Y. 2007. Noise Robust Speech Recognition Using Top-down selective Attention with an HMM Classifier. In IEEE Signal Processing Letters, 14, 489-491.
- MIN, S. Y. and BAE, M. J. 2001. On a Study of Decreasing the Processing Time in the Speech Recognition System Using The HMM Algorithm. In IEEE Proceedings, 1224-1228.
- Prasad, D. P. et al. 2001. Isolated Speech Recognition Using ANN, In Proceedings of the 23rd Annual EMBS International Conference, 1731-1734.
- Cong, L. et al. 2001. Robust Speech Recognition Using Neural Networks and HMM's. In Proceedings of ICASSP.
- Gemello, R. , Albesano, D. , Mana, F. 2000. CSELT Hybrid HMM/NN Technology for Continous Speech Recognition. In IEEE International Conference on Neural Networks, 103-108.
- Tsenov, G. T. and Mladenov, V. M. 2010. Speech Recognition using Neural Networks, Neural Network applications in Electrical Engineering, 181-186.
- Vapnik, V. 1995. The Nature of Statistical Learning Theory, Springer-verlag, New York, USA.
- Vapnik, V. N. 1998. Statistical Learning Theory, John Wiley & Sons, New York, USA.
- Burges, C. J. C. 1999. A Tutorial on Support Vector Machines for Pattern Recognition. http://svm. research. bell-labs. com/SVMdoc. html, AT&T Bell Labs.
- Joachims, T. 1999. SVMLight: Support Vector Machine, http://www. ai. informatik. unidortmund. de/FORSCHUNG/VERFAHREN/SVM_LIGHT/svm_light. eng. html,University of Dortmund.
- Ganapathiraju, A. , Hamaker, J. and Picone, J. 2000. Hybrid HMM/SVM Architectures for Speech Recognition, In Proceedings of the Department of Defense Hub 5 Workshop, College Park, Maryland, USA.
- Wu, K. P. and Wang, S. D. 2009. Choosing the Kernel Parameters for Support Vector Machines by the Inter-Cluster Distance in the Feature Space, In IEEE Transactions on Pattern Recognition, 42, 710-717.
- Rajeswari, Prasad, N. N. S. S. R. K. and Satyanarayana, V. 2012. Robust Speech Recognition using Wavelet Domain Front End and Hidden Markov Models. In Proceedings of International Conference on Emerging Research in Electronics, Computer science and Technology-ICERECT, Springer Lecture Notes-10. 1007/978-81-322-1157-0_44
- Chang, S. , Yu, B. , Vetterli, M. 2000. Adaptive Wavelet Thresholding for Image Denoising and Compression. In IEEE Transactions on Image Processing, 9, 1532-1546.
- Donoho, D. L. and Johnstone, I. M. 1995. De-noising by Soft-thresholding. In IEEE Transactions on Information Theory, 41, 613–627.
- Donoho, D. M. and Johnstone, I. M. 1995, Adapting to Unknown Smoothness via Wavelet Shrinkage. In Journal of the American Statistical Association, 90, 1200-1224.
- Sumithra, M. G. and Thanuskodi, K. 2009. Wavelet based Speech Signal De-Noising using Hybrid Thresholding, In conference proceedings of the International conference on Control, Automation, Communication and Energy Conservation.
- Jiang, H. et al. 2003. Feature Extraction Using wavelet Packet Strategy. In Proceedings of 42nd IEEE Conference on Decision and Control, 4517-4520.
- Gupta, M. and Gilbert, A. 2002. Robust Speech Recognition using Wavelet Coefficient Features, In IEEE Transactions on Speech and Audio Processing, 445-448.
- Florin, R. and Mititaru, D. 2010. A HMM/SVM Hybrid Method for Speaker Verification. In Proceedings of IEEE International Conference on Communication, 111-114.
Index Terms
Keywords