14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

New Cosine Similarity Scorings to Implement Gender-Independent Speaker Verification

Mohammed Senoussaoui (1), Patrick Kenny (2), Pierre Dumouchel (1), Najim Dehak (3)

(1) École de Technologie Supérieure, Canada
(2) CRIM, Canada
(3) MIT, USA

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 DCFfs, 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].


  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.

Full Paper

Bibliographic reference.  Senoussaoui, Mohammed / Kenny, Patrick / Dumouchel, Pierre / Dehak, Najim (2013): "New cosine similarity scorings to implement gender-independent speaker verification", In INTERSPEECH-2013, 2773-2777.