Abstract
Speaker verification is an important branch of speaker recognition. In this paper, a novel hierarchical speaker verification method based on TES-PCA Classifier and support vector machine plus Fuzzy c-means clustering was proposed for the sake of improving performance of speaker verification. In this algorithm, we utilized PCA and Fuzzy c-means clustering to select more discriminant and lower dimensional feature vectors firstly. And then, the truncation error space(TES) was obtained from PCA transformation matrix. The R target speakers were selected fleetly from TES-PCA classifier. Finally, support vector machine was used to make final decision. The experimental results showed that our proposed method could improve recognition accuracy remarkably and the system has better robustness compared with traditional methods.
This is a preview of subscription content, log in via an institution to check access.
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
Chao, Y.H.: Using LR-based discriminant kernel methods with applications to speaker verification. International Journal of Speech Communication 57(2), 76–86 (2014)
El-Gamal, M.A., Abu El-Yazeed, M.F., El Ayadi, M.M.H.: Dimensionality reduction for text-independent speaker identification using gaussian mixture model. In: IEEE International Symposium on Micro-Nano Mechatronics and Human Science, pp. 625–628. IEEE, Cairo (2003)
Zhang, W.F., Yang, Y.C., Wu, Z.H.: Exploiting PCA classifiers to speaker recognition. In: International Joint Conference on Neural Networks, pp. 820–823. IEEE, Portland (2003)
Xing, H.J., Hu, B.G.: An adaptive fuzzy c-means clustering-based mixtures of experts model for unlabeled data classification. Neurocomputing 71, 1008–1021 (2008)
Vapnik, V.: Universal Learning Technology: Support Vector Machines. NEC Journal of Advanced Technology 2(2), 137–144 (2005)
Zergat, K.Y., Amrouche, A.: New scheme based on GMM-PCA-SVM modelling for automatic speaker recognition. International Journal of Speech Technology 17(4), 373–381 (2014)
Zergat, K.Y., Amrouche, A.: SVM against GMM/SVM for dialect influence on automatic speaker recognition task. International Journal of Computational Intelligence and Applications 13(2), 1450012-1–1450012-10 (2014)
Suh, J.W., Lei, Y., Kim, W., Hansen, J.H.L.: Effective background data selection for SVM-based speaker recognition with unseen test environments: more is not always better. International Journal of Speech Technology 17(3), 211–221 (2014)
Vapnik, V.: The Nature of Statistical Leaning Theory, 2nd edn. Springer, New York (2000)
Renjifo, C., Barsic, D., Carmen, C., Norman, K., Peacock, G.S.: Improving radial basis function kernel classification through incremental learning and automatic parameter selection. Neurocomputing 72(13), 3–14 (2008)
Byrd, D.: Preliminary results on speaker-dependent variation in the TIMIT database. Journal of the Acoustical Society of America. 92(1), 593–596 (1992)
Gales, M.J.F., Young, S.J.: Robust continuous speech recognition using parallel model combination. IEEE Transactions on Speech & Audio Processing 4(5), 352–359 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Yujuan, X., Ping, T., Chengwen, Z. (2015). Speaker Verification Based on TES-PCA Classifier and SVM plus FCM Clustering. In: Yang, J., Yang, J., Sun, Z., Shan, S., Zheng, W., Feng, J. (eds) Biometric Recognition. CCBR 2015. Lecture Notes in Computer Science(), vol 9428. Springer, Cham. https://doi.org/10.1007/978-3-319-25417-3_55
Download citation
DOI: https://doi.org/10.1007/978-3-319-25417-3_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25416-6
Online ISBN: 978-3-319-25417-3
eBook Packages: Computer ScienceComputer Science (R0)