PLDA using Gaussian restricted Boltzmann machines with application to speaker verification

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 2, Issue , 2012, Pages 1690-1693

  Stafylakis, Themos ^a,b   Kenny, Patrick ^a   Senoussaoui, Mohammed ^a,b   Dumouchel, Pierre ^a,b  

^a Cent de Recherche Informatique de Montreal   (Canada)

^b ÉCOLE DE TECHNOLOGIE SUPÉRIEURE   (Canada)

Author keywords

Restricted Boltzmann Machines; Speaker Recognition

Indexed keywords

DIMENSIONALITY REDUCTION; FISHER'S DISCRIMINANT; GAUSSIAN RESTRICTED BOLTZMANN MACHINES; GRAPHICAL MODEL; RESTRICTED BOLTZMANN MACHINE; SPEAKER RECOGNITION; SPEAKER VERIFICATION; TRAINING ALGORITHMS;

COMPUTER APPLICATIONS; COMPUTER SIMULATION;

SPEECH RECOGNITION;

EID: 84878387361     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. N. Dehak, P. Kenny, R. Dehak, P. Dumouchel and P. Ouellet, "Front-End Factor Analysis for Speaker Verification", in IEEE Transactions on Audio, Speech & Language Processing, 2011.
2. P. Kenny, Bayesian Speaker Verification with Heavy-Tailed Priors in Proc. Odyssey Speaker and Language Recognition Workshop, Brno, Czech Republic, June 2010.
3. D. Garcia-Romero and C. Y. Espy-Wilso, Analysis of i-vector length normalization in speaker recognition systems, in Proceedings of Interspeech, Florence, Italy, Aug. 2011.
4. R. Salakhutdinov, "Learning Deep Generative Models", PhD thesis, University of Toronto, 2009.
5. G. E. Hinton. "Training products of experts by minimizing contrastive divergence". in Neural Computation, 14(8): 17111800, 2002.
6. S. J. D. Prince and J. H. Elder, Probabilistic linear discriminant analysis for inferences about identity", in Proc. ICCV 2007, Rio de Janeiro, Brazil, Oct. 2007.
7. G. E. Hinton, "A Practical Guide to Training Restricted Boltzmann Machines", Technical Report 2010003, Department of Computer Science, University of Toronto, 2010.
8. E. de Villiers and N. Brummer, BOSARIS toolkit, https://sites.google.com/ site/bosaristoolkit/.
9. M. Senoussaoui, P. Kenny, N. Brummer, E. de Villiers, P. Dumouchel: Mixture of PLDA models in I-vector space for gender independent speaker recognition, In Proc. of Interspeech 2011, Florence, Italy.