In this paper, a new simplified approach has been made for the design and implementation of a noise robust speech recognition using Multilayer Perceptron (MLP) based Artificial Neural Network and LPC-Cepstral Coefficient. Cepstral matrices obtained via Linear Prediction Coefficient are chosen as the eligible features. Here, MLP neural network based transformation method is studied for environmental mismatch compensation. MLP based neural network has been used by many researchers in conjunction with speech recognition, basically for the transformation of the speech feature vectors. In our current study, neural network (MLP) is used to compensate for the environmental mismatch either in feature domain, the model domain, or both. It has been observed that environmental mismatch is automatically compensated without particular knowledge of the environmental interference and retraining. This method can be applied to both linear and non-linear distortion of the speech signal, such as in noisy reverberant speech or telephone speech. Further it can be used for speaker adaptation. By using MLP based neural network, the adaptation processes would require small volume of training data. The Assamese and Bodo are two local languages of North-East India, and they are used as reference languages to carry out this study.

1. Dongsuk, Y.: Robust Speech Recognition Using Neural Network and Hidden Markov Models, Ph. D. Dissertation, 1999.
2. Gong, Y.: Speech Recognition in Noisy Environments: A Survey, Speech Communication, 16(3):261-291., April 1995.
3. Junqua, J. and Haton, J.: Robustness in Automatic Speech Recognition, Kluwer Academic Publishers, 1996.
4. Lang, k. and Waibel, A.: A time-delay neural network architecture for isolated word recognition, Neural Networks, 3:23–43, 1990.
5. Lippmann, R.; Martin, E. and Paul, D.: Multi-Style Training for Robust Isolated-Word Speech Recognition, IEEE International Conference on Acoustics, Speech and Signal Processing, 705-708, April 1987.
6. Morgan, N. and Bourlard, H.: Neural networks for statistical recognition of continuous speech, Proceedings of the IEEE, 83(5):742–770, May 1995.
7. Renals, S.; Morgan, N.; Bourlard, H; Cohen, M. and Franco, H.: Connectionist probability estimators in HMM speech recognition, IEEE Transactions on Speech and Audio Processing, 2(1):161–173, January 1994.
8. Sorensen, H.: A Cepstral Noise Reduction Multi-Layer Neural Network, IEEE International Conference on Acoustics, Speech and Signal Processing, 1:933-936, May 1991.
9. Talukdar, P.H.; Bhattacharjee, U.; Goswami, C.K. and Barman, J.: Cepstral Measure of Bodo Vowels Through LPC-Analysis, Journal of the CSI, Vol. 34 No-1, Jan-Mar, 2004.
10. Talukdar, P.H.; Bhattacharjee, U.; Goswami, C.K. and Barman, J.: Formants Analysis of Bodo/Boro Vowels with References to Japanese Vowels, Prajna Vol. XII, 56-64, 2002-2003.
11. Waibel, A.; Hanazawa, T.; Hinton, G.; Shikano, K. and Lang, K.: Phoneme recognition using time-delay neural networks, IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(3):328–339, March 1989.
12. Yuk, D.: A study on Korean phoneme recognition, Master’s thesis, Korea University, 1993.

Linear Predictive (LPC) Cepstral Coefficient Artificial Neural Network Multilayer Perceptron (MLP) Feature Vector Assamese Language Bodo Language