Abstract
An effective global impostor selection method is proposed in this paper for discriminative Deep Belief Networks (DBN) in the context of a multi-session i-vector based speaker recognition. The proposed method is an iterative process in which in each iteration the whole impostor i-vector dataset is divided randomly into two subsets. The impostors in one subset which are closer to each impostor in another subset are selected and impostor frequencies are computed. At the end, those impostors with higher frequencies will be the global selected ones. They are then clustered and the centroids are considered as the final impostors for the DBN speaker models. The advantage of the proposed method is that in contrary to other similar approaches, only the background i-vector dataset is employed. The experimental results are performed on the NIST 2014 i-vector challenge dataset and it is shown that the proposed selection method improves the performance of the DBN-based system in terms of minDCF by 7% and the whole system outperforms the baseline in the challenge by more than 22% relative improvement.
Index Terms: Speaker Recognition, Deep Belief Network, Impostor Selection, NIST i-vector challenge.
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.
Similar content being viewed by others
References
Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-End Factor Analysis for Speaker Verification. IEEE Transactions on Audio, Speech, and Language Processing 19, 788–798 (2011)
Prince, S., Elder, J.: Probabilistic Linear Discriminant Analysis for Inferences About Identity. In: IEEE 11th International Conference on Computer Vision, ICCV 2007 (2007)
Kenny, P.: Bayesian speaker verification with heavy tailed priors. In: IEEE Odyssey Speaker and Language Recognition Workshop (2010)
Brummer, N., Villiers, E.: The speaker partitioning problem. In: Proceedings of the Odyssey Speaker and Language Recognition Workshop, Brno, Czech Republic (2010)
Liu, G., Hasan, T., Boril, H., Hansen, J.: An investigation on back-end for speaker recognition in multi-session enrollment. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7755–7759 (2013)
Larcher, A., Lee, K., Ma, B., Li, H.: Phonetically-constrained PLDA modeling for text-dependent speaker verification with multiple short utterances. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7673–7677 (2013)
Larcher, A., Bonastre, J.-F., Fauve, B., Lee, K., Lvy, C., Li, H., Mason, J., Parfait, J.-Y.: ALIZE 3.0 Open Source Toolkit for State-of-the-Art Speaker Recognition. In: Proc. Interspeech, pp. 2768–2771 (2013)
The 2013-2014 Speaker Recognition i-vector Machine Learning Challenge (2014)
Khoury, E., El Shafey, L., Ferras, M., Marcel, S.: Hierarchical speaker clustering methods for the NIST i-vector Challenge. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 254–259 (2014)
Novoselov, S., Pekhovsky, T., Simonchik, K.: STC Speaker Recognition System for the NIST i-Vector Challenge. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 231–240 (2014)
Vesnicer, B., Zganec-Gros, J., Dobrisek, S., Struc, V.: Incorporating Duration Information into I-Vector-Based Speaker-Recognition Systems. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 241–248 (2014)
Khosravani, A., Homayounpour, M.: Linearly Constrained Minimum Variance for Robust I-vector Based Speaker Recognition. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 249–253 (2014)
Ghahabi, O., Hernando, J.: i-Vector Modeling with Deep Belief Networks for Multi-Session Speaker Recognition. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 305–310 (2014)
McLaren, M., Baker, B., Vogt, R., Sridharan, S.: Improved SVM speaker verification through data-driven background dataset collection. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, pp. 4041–4044 (2009)
Liu, G., Suh, J.-W., Hansen, J.: A fast speaker verification with universal background support data selection. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4793–4796 (2012)
Ghahabi, O., Hernando, J.: Deep belief networks for i-vector based speaker recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014)
Hinton, G., Osindero, S., Teh, Y.-W.: A Fast Learning Algorithm for Deep Belief Nets. Neural Computation 18, 1527–1554 (2006)
Hinton, G., Salakhutdinov, R.: Reducing the Dimensionality of Data with Neural Networks. Science 313, 504–507 (2006)
Hinton, G.E.: A Practical Guide to Training Restricted Boltzmann Machines. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) NN: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 599–619. Springer, Heidelberg (2012)
Dahl, G., Yu, D., Deng, L., Acero, A.: Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing 20, 30–42 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ghahabi, O., Hernando, J. (2014). Global Impostor Selection for DBNs in Multi-session i-Vector Speaker Recognition. In: Navarro Mesa, J.L., et al. Advances in Speech and Language Technologies for Iberian Languages. Lecture Notes in Computer Science(), vol 8854. Springer, Cham. https://doi.org/10.1007/978-3-319-13623-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-13623-3_10
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13622-6
Online ISBN: 978-3-319-13623-3
eBook Packages: Computer ScienceComputer Science (R0)