An Advanced Method for Speech Recognition

In this paper in consideration of each available techniques deficiencies for speech recognition, an advanced method is presented that-s able to classify speech signals with the high accuracy (98%) at the minimum time. In the presented method, first, the recorded signal is preprocessed that this section includes denoising with Mels Frequency Cepstral Analysis and feature extraction using discrete wavelet transform (DWT) coefficients; Then these features are fed to Multilayer Perceptron (MLP) network for classification. Finally, after training of neural network effective features are selected with UTA algorithm.

Authors:

• Meysam Mohamad pour
• Fardad Farokhi

Keywords:

• Multilayer perceptron (MLP) neural network
• Discrete Wavelet Transform (DWT)
• Mels Scale Frequency Filter
• UTA algorithm.

References:

[1] Abdul Ahad, Ahsan Fayyaz, Tariq Mehmood. "Speech Recognition
using Multilayer Perceptron" . IEEE trans. pp.103,2002.
[2] Karina Vieira, Bogdan Wilamowski, and Robert Kubichek " Speaker
Verification for Security Systems Using Artificial Neural Networks".
IEEE trans. pp.1102-1105,2003.
[3] Song Yang, Meng Joo Er, and Yang Gao. "A High Performance Neural-
Networks-Based Speech Recognition System". IEEE trans.
pp.1527,2001.
[4] Keogh, E. & M. Pazzani. "Derivative Dynamic Time Warping". In Proc.
of the First Intl. SIAM Intl. Conf. on Data Mining, Chicago, Illinois,
2001.
[5] Abdulla, W., D. Chow, and G. Sin, "Cross-words reference template for
DTW-based speech recognition systems", in Proc. IEEE TENCON,
Bangalore, India, 2003.
[6] Corneliu Octavian DUMITRU, Inge GAVAT. "Vowel, Digit and
Continuous Speech Recognition Based on Statistical, Neural and Hybrid
Modelling by Using ASRS_RL ". EUROCON 2007, The International
Conference on "Computer as Tool", pp.858-859.
[7] i.Gavat, O.Dumitru, C. Iancu, Gostache, "Learning strategies in speech
Recognition", Proc. Elmar 2005, pp.237-240, june 2005,Zadar, Croatia.
[8] Bahlmann. Haasdonk. Burkhardt. "speech and audio recognition" .
IEEE trans. Vol 11. May 2003.
[9] Edward Gatt, Joseph Micallef, Paul Micsllef, Edward Chilton.
"Phoneme Classification in Hardware Implemented Neural Networks ".
IEEE trans, pp.481, 2001.
[10] Redondo, M.F. Espinosa, C.H. "A comparison among feature selection
methods based on trainednetworks." IEEE trans.Aug1999
[11] Kirschning. 1. "Continuous Speech Recognition Using the Time-Sliced
Paradigm", MEng.Dissertation, University Of Tokushinia, 1998.
[12] Tebelskis. J. "Speech Recognition Using Neural Networks", PhD.
Dissertation, School Of ComputerScience, Carnegie Mellon University,
1995.
[13] J. Tchorz, B. Kollmeier; "A Psychoacoustical Model of the Auditory
Periphery as Front-end forASR"; ASAEAAiDEGA Joint Meeting on
Acoustics; Berlin, March 1999.
[14] Cory L. Clark "LabVIEW Digital Signal Processing and Digital
Communications". McGraw-Hill Companies.2005
[15] " Digital Signal Processing System-Level Design Using LabVIEW " by
Nasser Kehtarnavaz and Namjin Kim University of Texas at Dallas.
2005.
[16] M. Kantardzic. Data Mining Concepts, Models, Methods, and
Algorithms. IEEE, Piscataway, NJ, USA, 2003.
[17] R.P. Lippmann, "An Introduction to computing with neural nets." IEEE
ASSP Mag. , vol 4, Apr.1997
[18] H. B. D. Martin T. Hagan and M. Beale. Neural Network Design. PWS
Publishing Company, Boston, MA, USA, 1996.
[19] T. G. Dietterich. Machine learning for sequential data: A review. In
Proceedings of the Joint IAPR International Workshop on Structural,
Syntactic, and Statistical Pattern Recognition, pp.15-30, 2002. Springer-
Verlag, London, UK.
[20] MathWorks. Neural Network Toolbox User-s Guide, 2004.
[21] S.M Peeling, R.K Moore and R.J.Tomlinson, "TheMulti Layer
Perceptron as a tool for speech pattern processing research." in Proc.
IoA Autumn Conf.Speech Hearing. 1986.