KASHMIRI SPEECH RECOGNITION SYSTEM USING LINEAR PREDICTIVE CODING AND ARTIFICIAL NEURAL NETWORKS

Volume: 2    Issue: 6

Year of Publication: 2015

Pages: (20-23)

Authors: Aabid Rashid Wani, Er. Tabish Gulzar, Er. Mamoon Rashid

Download Full Text (PDF)

Abstract

This paper suggests an approach to recognize Kashmiri words corresponding to digits zero (safer) to Nine (Nov) spoken in an isolated way by different male and female speakers. The study performs feature extraction for isolated word recognition using Linear Predictive Coding (LPC) and Artificial Neural Network (ANN). The dataset comprising of males and females voices were trained and tested where each word has been repeated 5 times by the speakers. An accuracy of 92% is acquired by the combination of features, when the suggested approach is verified using a dataset of 350 speech samples, which is excess than those acquired by using the features singly.

References

1. L.R. Rabiner and R.W. Schafer, Digital Processing of Speech Signals,Prentice-Hall, Englewood Cliffs, 1978.

2. L. Rabiner and G. Juang, “Fundamentals of Speech Recognition,” Prentice-Hall, 1993.

3. M. Eunus Ali, “An Approach to Implementation of Bangla Speech Recognition using Hidden Markov Model,” A Thesis Paper, Dept. of Computer Science and Engineering, BUET,Dhaka.

4. J. Tebelskis, “Speech Recognition Using Neural Networks,” PhD Dissertation, Carnegie Mellon University, 1995.

5. H. Hasegawa, M. Inazumi, “Speech Recognition by Dynamic Recurrent Neural Networks,”Proceedings of 1993 International Joint Conference on Neural Networks.

6. David J. DeFatta, Joseph G. Lucas, William S.Hodgkiss, “Digital Signal Processing: A System Design Approach,” John Willy & Sons, Inc.,1998

7. M.N. Minhaz, M.S. Rahamn and S.M. Rahamn,“Feature Extraction for Speaker Identification,”Int. Conf. on Comp. and Info. Tech., Dhaka,December 18-20, 1998

8. Rabiner, L.R. and Juang, B.H 1993, Fundamentals of speech recognition, 1st Indian Reprint, Pearson Education.

9. Qi Li, Zheng, J., Tsai, A.and Zhou, Q. 2002, Robust Endpoint Detection and Energy Normalization for Real- Time Speech and Speaker Recognition, IEEE Transactions on speech and audio processing, Vol.10, NO.3.

10. Tanyer, S.G. and Özer, H. 2000, Voice Activity Detection in Non Stationary Noise, IEEE Transactions on speech and audio processing, Vol. 8, NO. 4.

11. Qi.Li and Tsai, A. 1999, A language- independent personal voice controller with embedded speaker verification, in Proc. Eurospeech’99, Budapest, Hungary.

12. L.R. Rabiner and R.W.Schafer, ,“Digital Signal Processing for Man-Machine Communication by Voice” in Digital processing of Speech Signals, 3rd ed.Pearson Education,2009,pp. 505-516

13. L.R.Rabiner and M.R.Sambur, ,“An Algorithm for Determining the Endpoints of Isolated Utterances”Bell Syst.Tech.J.,vol.24,no.2,pp.297-315,1975

14. B.S.Atal, ,“Effectiveness of linear prediction characteristics of the speech wave fpr automatic speaker identification and verification,”J.Acoust.Soc.Am.,vol.55,no.6,pp.1304-1312,1974

15. Ahmad A.M.Abushariah,Teddy S. Gunawan,et. al., ,“English Digits Speech Recognition Based on Hidden Markov Models,”ICCCE, Kuala Lampur,Malaysia,May 2010.

Keywords

LPC, ANN, Extraction, Kashmiri, Database.