Hybrid wavelet based LPC features for Hindi speech recognition

被引：18

作者：

Sharma, Aditya ^{[1
]}

Shrotriya, M.C. ^{[2
]}

Farooq, Omar ^{[1
]}

Abbasi, Z.A. ^{[1
]}

机构：

[1] Department of Electronics Engineering, AMU, Aligarh

[2] Department of Electronics and Communication Engineering, Birla Institute of Technology, Mesra Ranchi

来源：

International Journal of Information and Communication Technology | 2008年 / 1卷 / 3-4期

关键词：

Hidden Markov model; Hindi digits recognition; HMM; Hybrid features; Linear discriminant analyser; Wavelet transform;

D O I：

10.1504/IJICT.2008.024008

中图分类号：

学科分类号：

摘要：

Hybrid features are presented for speech recognition that uses linear prediction in combination with multi-resolution capabilities of wavelet transform. Wavelet-Based Linear Prediction Coefficients (WBLPC) are obtained by applying 3 and 4-level wavelet decomposition and then having linear prediction of each sub-bands to get total 13 features. These features have been tested using a linear discriminant function and Hidden Markov Model (HMM) based classifier for speaker dependent and independent isolated Hindi digits recognition. 3-level WBLPC features gave higher percentage recognition than LPC features while 4-level WBLPC features using HMM gave the highest percentage recognition for both speaker dependent and independent cases. Copyright © 2008, Inderscience Publishers.

引用

页码：373 / 381

页数：8

共 18 条

[1]

Athineos M., Ellis D.P., Frequency-domain linear prediction for temporal features, Proc. ASRU, pp. 261-266, (2003)

[2]

Chang S., Kwon Y., Yang S., Speech feature extracted from adaptive wavelet for speech recognition, Electronics Letters, 34, pp. 2211-2213, (1998)

[3]

Duda R.O., Hart P.E., Stork G., Pattern Classification, (2001)

[4]

Farooq O., Datta S., Mel filter-like admissible wavelet packet structure for speech recognition, IEEE Signal Processing Letters, 8, 7, pp. 196-198, (2001)

[5]

Hermansky H., Perceptual linear predictive (PLP) analysis for speech, Journal of the Acousticstical Society of America, 87, 4, pp. 1738-1752, (1990)

[6]

Katz M., Meier H.-G., Dolfing H., Klakow D., Robustness of linear discriminant analysis in automatic speech recognition, Proc. International Conference on Pattern Recognition, 3, pp. 30371-30374, (2002)

[7]

Krishnan M., Neophytou C.P., Prescott G., Wavelet transform speech recognition using vector quantization, dynamic time warping and artificial neural networks, International Conference on Spoken Language Processing, (1994)

[8]

Kumar M., Rajput N., Verma A., A large vocabulary continuous speech recognition system for Hindi, IBM Journal of Research and Development, 48, 5-6, pp. 703-714, (2004)

[9]

Lee C., Hyun D., Choi E., Go J., Lee C., Optimizing feature extraction for speech recognition, IEEE Trans. Speech and Audio Processing, 11, 1, pp. 80-87, (2003)

[10]

Lung S.Y., Wavelet feature selection using fuzzy approach to text independent speaker recognition, IEICE Trans. Fundamentals, E88-A, 3, pp. 779-781, (2005)

← 1 2 →