Abstract
MFCC features are widely used in speech recognition. However MFCCs are not suitable for identifying a speaker since they should be located in high-frequency regions while the Mel scale gets coarser in the higher-frequency bands. The speaker’s individual information, which is nonuniformly distributed in the high-frequency bands, is equally important for speaker recognition. Accordingly, wavelet-based features are more appropriate.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
V. Tiwari, J. Singhai, Wavelet based noise robust features for speaker recognition. Signal Process. Int. J. (SPIJ) 5(2), 52–64 (2011)
T. Kinnunen, H. Li, An overview of text-independent speaker recognition: from features to supervectors. Speech Comm. 52(1), 12–40 (2010)
T. Ganchev, M. Siafarikas, I. Mporas, T. Stoyanova, Wavelet basis selection for enhanced speech parametrization in speaker verification. Int. J. Speech Technol. 17(1), 27–36 (2014)
T. Ganchev, M. Siafarikas, N. Fakotakis, Speaker Verification Based on Wavelet Packets, Lecture Notes in Computer Science, vol LNAI 3206/2004 (Springer, Heidelberg, 2004), pp. 299–306
M. Siafarikas, T. Ganchev, N. Fakotakis, G. Kokkinakis, Wavelet packet approximation of critical bands for speaker verification. Int. J. Speech Technol. 10(4), 197–218 (2007)
N. Zheng, T. Lee, P. Ching, Integration of complementary acoustic features for speaker recognition. IEEE Signal Process. Lett. 14(3), 181–184 (2007)
S.M. Deshpande, R.S. Holambe, Speaker identification using admissible wavelet packet based decomposition. Int. J. Inf. Commun. Eng 6(1), 20–23 (2010)
K.D. Returi, Y. Radhika, An artificial neural networks model by using wavelet analysis for speaker recognition, in Information Systems Design and Intelligent Applications. Advances in Intelligent Systems and Computing, ed. by J. Mandal, S. Satapathy, M. Kumar Sanyal, P. Sarkar, A. Mukhopadhyay, vol. 340, (Springer, New Delhi, 2015), pp. 859–874
C. Turner, A. Joseph, A wavelet packet and Mel-frequency Cepstral coefficients-based feature extraction method for speaker identification. Procedia Comput. Sci. 61, 416–421 (2015)
D. Avci, An expert system for speaker identification using adaptive wavelet SURE entropy. Expert Syst. Appl. 36(3), Part 2, 6295–6300 (2009)
E. Avci, A new optimum feature extraction and classification method for speaker recognition: GWPNN. Expert Syst. Appl. 32(2), 485–498 (2007)
B. Ziółko, W. Kozłowski, M. Ziółko, R. Samborski, D. Sierra, J. Gałka, Hybrid wavelet-Fourier-HMM speaker recognition. Int. J. Hybrid Inf. Technol. 4(4), 25–42 (2011)
K. Daqrouq, T.A. Tutunji, Speaker identification using vowels features through a combined method of formants, wavelets, and neural network classifiers. Appl. Soft Comput. 27(C), 231–239 (2015)
L. Lei, S. Kun, Speaker recognition using wavelet cepstral coefficient, i-vector, and cosine distance scoring and its application for forensics. J. Electr. Comput. Eng. 2016, 11 (2016)
S.M. Govindan, P. Duraisamy, X. Yuan, Adaptive wavelet shrinkage for noise robust speaker recognition. Digit. Signal Process. 33, 180–190 (2014)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2018 The Author(s)
About this chapter
Cite this chapter
Farouk, M.H. (2018). Speaker Identification. In: Application of Wavelets in Speech Processing. SpringerBriefs in Electrical and Computer Engineering(). Springer, Cham. https://doi.org/10.1007/978-3-319-69002-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-69002-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69001-8
Online ISBN: 978-3-319-69002-5
eBook Packages: EngineeringEngineering (R0)