Faculty of Information Technology, BUT

Publication Details

Gender Independent Discriminative Speaker Recognition in I-Vector Space

CUMANI Sandro, GLEMBEK Ondřej, BRUMMER Niko, DE Villiers Edward and LAFACE Pietro. Gender Independent Discriminative Speaker Recognition in I-Vector Space. In: Proc. International Conference on Acoustics, Speech, and Signal P. Kyoto: IEEE Signal Processing Society, 2012, pp. 4361-4364. ISBN 978-1-4673-0044-5.
Czech title
Diskriminativní rozpoznávání mluvčího v i-vektorovém prostoru nezávislé na pohlaví
Type
conference paper
Language
english
Authors
Cumani Sandro (POLITO)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Brummer Niko (Agnitio)
de Villiers Edward (Agnitio)
Laface Pietro, prof. (POLITO)
URL
Keywords
speaker recognition, gender recognition, PLDA models, GI Pairwise SVM
Abstract
This paper describes speaker recognition systems that are trained with gender dependent features and tested with known gender trails.
Annotation
Speaker recognition systems attain their best accuracy when trained with gender dependent features and tested with known gender trials. In real applications, howevcer, gender labels are often not given. In this work we illustrate the design of a system that does not make use of the gender labels both in training and in test, i.e. a completely Gender Independent (GI) system. It relies on discriminative training, where the trials are i-vector pairs, and the discrimination is between the hypothesis that the pair of feature vectors in the trial belong to the same speaker or to different speakers. We demonstrate that this pairwise discriminative training can be interpreted as a procedure that estimates the parameters of the best (second order) approximation of the log-likelihood ratio score function, and that a pairwise SVM can be used for training a gender independent system. Our results show that a pairwise GI SVM, saving memory and execution time, achieves on the last NIST evaluationscomplet state-of-the-art performance, comparable to a Gender Dependent(GD) system.
Published
2012
Pages
4361-4364
Proceedings
Proc. International Conference on Acoustics, Speech, and Signal P
Conference
The 37th International Conference on Acoustics, Speech, and Signal Processing, Kyoto, JP
ISBN
978-1-4673-0044-5
Publisher
IEEE Signal Processing Society
Place
Kyoto, JP
DOI
BibTeX
@INPROCEEDINGS{FITPUB9942,
   author = "Sandro Cumani and Ond\v{r}ej Glembek and Niko Brummer and Edward Villiers de and Pietro Laface",
   title = "Gender Independent Discriminative Speaker Recognition in I-Vector Space",
   pages = "4361--4364",
   booktitle = "Proc. International Conference on Acoustics, Speech, and Signal P",
   year = 2012,
   location = "Kyoto, JP",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4673-0044-5",
   doi = "10.1109/ICASSP.2012.6288885",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9942"
}
Back to top