Abstract
Kernel-PCA and PCA techniques are compared in the task of age and gender separation. A feature extraction process that discriminates between vocal tract and glottal source is implemented. The reason why speech is processed in that way is because vocal tract length and resonant characteristics are related to gender and age and there is also a great relationship between glottal source and age and gender. The obtained features are then processed with PCA and kernel-PCA techniques. The results show that gender and age separation is possible and that kernel-PCA (especially with RBF kernel) clearly outperforms classical PCA or no preprocessing features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Schötz, S.: Acoustic Analysis of Adult Speaker Age. In: Müller, C. (ed.) Speaker Classification 2007. LNCS (LNAI), vol. 4343, pp. 88–107. Springer, Heidelberg (2007)
Molina – Hurtado, M.T., et al.: Voz del niño. Rev. Med. Univ. Navarra 50(3), 31–43 (2006)
Fernández- González, S., et al.: Voz del anciano. Rev. Med. Univ. Navarra 50(3), 44–48 (2006)
Raj, A., et al.: A Study of Voice Changes in Various Phases of Menstrual Cycle and in postmenopausal Women. Journal of Voice 24(3), 363–368 (2010)
Shafran, I., et al.: Voice Signatures. In: Proc. of Automatic Speech Recognition and understanding Workshop (ASRU) (2003)
Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10(5), 1299–1319 (1998)
Moreno, A., Poch, D., Bonafonte, A., Lleida, E., Llisterri, J., Marío, J.B., Nadeu, C.: Albayzin Speech Database: Design of the Phonetic Corpus. In: Eurospeech 1993, Berlin, Germany, vol. 1, pp. 653–656 (September 1993)
Gomez, P., Álvarez, A., Mazaira, L.M., Fernández, R., Nieto, V., Martínez, R., Muñoz, C., Rodellar, V.: A Hybrid Parameterization Technique for Speaker Identification. In: Proceedings of the EUSIPCO 2008-paper 1569104632, Laussane, Switzerland (2008)
Gómez-Vilda, P., et al.: Glottal source biometrical signature for voice pathology detection. Journal Speech Comunication 51(9) (September 2009)
Minematsu, N., et al.: Performance Improvement in Estimating Subjetive Agedeness with Prosodic Features. In: Proc. Speech Prosody (2002)
Minematsu, N., et al.: Automatic Estimation of One’s Age with His/Her Speech Based upon Acoustic Modeling Techniques of Speakers. In: Proc. ICASSP, pp. 137–140 (2005)
Müller, C., et al.: Exploiting Speech for Recognizing Elderly Users to Respond to their Special Needs. In: Proc. EUROSPEECH (2003)
Müller, C.: Automatic Recognition of Speakers’ Age and Gender on the Basis of Empirical Studies. In: Proc. INTERSPEECH (2006)
Sedaaghi, M.H.: A Comparative Study of Gender and Age Classification in Speech Signals. Iranian Journal of Electrical & Electronic Engineering 5(1) (March 2009)
Muñoz- Mulas, C., Martínez-Olalla,R., Álvarez-Marquina, A., Mazaira-Fernández, L.M., Gómez Vilda, P.: Discriminación de género basada en nuevos parámetros MFCC’.1er WTM-IP, Gran Canarias (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Muñoz-Mulas, C. et al. (2011). KPCA vs. PCA Study for an Age Classification of Speakers. In: Travieso-González, C.M., Alonso-Hernández, J.B. (eds) Advances in Nonlinear Speech Processing. NOLISP 2011. Lecture Notes in Computer Science(), vol 7015. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25020-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-25020-0_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25019-4
Online ISBN: 978-3-642-25020-0
eBook Packages: Computer ScienceComputer Science (R0)