Abstract | ||
---|---|---|
This work presents a new approach to discriminative speaker verification. Rather than estimating speaker models, or a model that discriminates between a speaker class and the class of all the other speakers, we directly solve the problem of classifying pairs of utterances as belonging to the same speaker or not. The paper illustrates the development of a suitable Support Vector Machine kernel from a state-of-the-art generative formulation, and proposes an efficient approach to train discriminative models. The results of the experiments performed on the tel-tel extended core condition of the NIST 2010 Speaker Recognition Evaluation are competitive or better, in terms of normalized Decision Cost Function and Equal Error Rate, compared to the more expensive generative models. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5947442 | Acoustics, Speech and Signal Processing |
Keywords | DocType | ISSN |
speaker recognition,support vector machines,I-vector space,NIST 2010 speaker recognition evaluation,decision cost function,discriminative models,equal error rate,fast discriminative speaker verification,speaker models,support vector machine kernel,tel-tel extended core condition,Discriminative Training,Support Vector Machines,Two-covariance Kernel,i-vectors | Conference | 1520-6149 E-ISBN : 978-1-4577-0537-3 |
ISBN | Citations | PageRank |
978-1-4577-0537-3 | 11 | 0.86 |
References | Authors | |
6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sandro Cumani | 1 | 200 | 18.81 |
Niko Brümmer | 2 | 595 | 44.01 |
Lukas Burget | 3 | 12 | 1.22 |
Pietro Laface | 4 | 378 | 60.68 |