Summary
This paper presents the use of discrete wavelet transform for feature extraction of phoneme. Instead of using the conventional wavelet coefficients, energy per sample is calculated in different frequency bands and used as features. Training and test samples of the phonemes were obtained from the TIMIT database from the dialect region DR1 and DR2. Features extracted were updated every 8ms to account for the non-stationary property of the speech signal. For the classification of the phonemes two different classifiers were used based on Linear Discriminant Analysis (LDA) and Multi-Layer Perceptron (MLP). The results obtained show high speaker independent recognition rate by both the classifiers. The recognition rates obtained by using MLP classifier were found to be about 3–10% higher than the LDA for different number offeatures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Beng T. Tan, Minyue Fu, Andrew Spray and Phillip Dermody, “The use of wavelet transform for phoneme recognition”, Proceeding of 4th Int. Conf. of Spoken Language Processing Philadelphia, USA Oct. 3–6 1996, Vol. 4, pp. 2431–2434.
Stéphane Mallat, “A wavelet tour of signal processing”, Academic Press, 1998.
Sungwook Chang, Y. Kwon and Sung-il Yang, “Speech feature extracted from adaptive wavelet for speech recognition”, Electronic Letters, Vol 134, No. 23, 12th Nov. 1998, pp. 2211–2213.
TIMIT Acoustic-Phonetic Continuous Speech Corpus, National Institute of Standards and Technology, Speech Disc 1–1.1, Oct. 1990, NTIS Order No. PB91–505065.
Olivier Rioul and Martin Vetterli, “Wavelet and signal processing”, IEEE Signal Processing Mag., Oct. 1991, pp. 14–38.
C. J. Long and S. Datta, “Wavelet based feature extraction for phoneme recognition”, Proc. of 4th Int. Conf. of Spoken Language Processing Philadelphia, USA Oct. 3–6 1996, Vol. 1, pp. 264–267.
C. J. Long and S. Datta, “Discriminant wavelet basis construction for speech recognition”, Proc. of 5th Int. Conf. of Spoken Language Processing Sydney, Australia 30th Nov-4th Dec. 1998, Vol. 3, pp. 1047–1049.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Farooq, O., Datta, S. (2001). A Neural Network Phoneme Classification Based on Wavelet Features. In: John, R., Birkenhead, R. (eds) Developments in Soft Computing. Advances in Soft Computing, vol 9. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1829-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1829-1_9
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1361-6
Online ISBN: 978-3-7908-1829-1
eBook Packages: Springer Book Archive