Abstract
This paper compares performances between GMM-UBM classifier and SVM classifier with GMM supervector as the linear kernel for text-independent speaker verification. The MFCC feature set has been used for this comparison. Experimental evaluation was conducted on the POLYCOST database. The importance of utterance partitioning for training speech has been discussed. Results reveal that, without utterance partitioning, the accuracy of SVM classifier with GMM supervectors for small test segment is poor. For proper utterance partitioning of the training speech, the SVM classifier with GMM supervectors performs significantly better compared to GMM-UBM baseline. The detailed derivation of GMM supervector has also been discussed.
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
Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker Verification Using Gaussian Mixture Models. Digital Signal Processing 10, 19–41 (2000)
Cristianini, N., Taylor, J.S.: Support Vector Machines. Cambridge University Press, Cambridge (2000)
Campbell, W.M., Sturim, D.E., Reynolds, D.A.: Support Vector Machines using GMM Supervectors for Speaker Verification. IEEE Signal Processing Lett. 13, 308–311 (2006)
Mak, M.W., Rao, W.: Utterance partitioning with acoustic vector resampling for GMM-SVM speaker verification. Speech Communication 53, 119–130 (2011)
Petrovska, D., et al.: POLYCOST: A Telephonic speech database for speaker recognition. In: RLA2C, Avignon, France, April 20-23, pp. 211–214 (1998)
Hsu, C.W., Chang, C.C., Lin, C.J.: A Practical Guide to Support Vector Classification, http://www.csie.ntu.edu.tw/~cjlin/libsvm
Campbell, J.P.: Speaker Recognition: A Tutorial. Proceedings of the IEEE 85(9), 1437–1462 (1997)
Do, M.N.: Fast approximation of Kullback–Leibler distance for dependence trees and hidden Markov models. IEEE Signal Processing Lett. 10(4), 115–118 (2003)
Davis, S.B., Mermelsteine, P.: Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust., Speech, Signal Processing ASSP-28(4), 357–365 (1980)
Sahidullah, M., Saha, G.: Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Communication 54(4), 543–565 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Sen, N., Patil, H.A., Mandal, S.K.D., Rao, K.S. (2013). Importance of Utterance Partitioning in SVM Classifier with GMM Supervectors for Text-Independent Speaker Verification. In: Prasath, R., Kathirvalavakumar, T. (eds) Mining Intelligence and Knowledge Exploration. Lecture Notes in Computer Science(), vol 8284. Springer, Cham. https://doi.org/10.1007/978-3-319-03844-5_76
Download citation
DOI: https://doi.org/10.1007/978-3-319-03844-5_76
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03843-8
Online ISBN: 978-3-319-03844-5
eBook Packages: Computer ScienceComputer Science (R0)