This paper is a natural extension of our previous work on genderindependent speaker verification systems [1]. In a previous paper, we presented a solution to avoid using gender information in the Probabilistic Linear Discriminant Analysis (PLDA) without any loss of accuracy compared with a gender-dependent base-line implementation. In this work, we propose two solutions to make a speaker verification system based on Cosine similarity independent of speaker gender. Our choice of the Cosine similarity is motivated by the fact that it is proved itself as a second state-of-the art . in parallel with PLDA. of i-vector based speaker verification systems. As measured by Equal Error Rate and min DCFfs, performance results on the extended telephone list coreext-coreext condition of SRE2010 show no performance decrease in gender-independent Cosine similarity system compared to gender-dependent one. Tests were also successful for gender-independent propositions on a cross gender list as done in [1].
M. Senoussaoui, P. Kenny, N. Brummer, E. de Villiers and P. Dumouchel, Mixture of PLDA Models in I-Vector Space for Gender-Independent Speaker Recognition, in INTERSPEECH-2011, this archive.
Cite as: Senoussaoui, M., Kenny, P., Dumouchel, P., Dehak, N. (2013) New cosine similarity scorings to implement gender-independent speaker verification. Proc. Interspeech 2013, 2773-2777, doi: 10.21437/Interspeech.2013-635
@inproceedings{senoussaoui13_interspeech,
author={Mohammed Senoussaoui and Patrick Kenny and Pierre Dumouchel and Najim Dehak},
title={{New cosine similarity scorings to implement gender-independent speaker verification}},
year=2013,
booktitle={Proc. Interspeech 2013},
pages={2773--2777},
doi={10.21437/Interspeech.2013-635}
}