ISCA Archive Odyssey 2008
ISCA Archive Odyssey 2008

ALIZE/spkdet: a state-of-the-art open source software for speaker recognition

Jean-Francois Bonastre, Nicolas Scheffer, Driss Matrouf, Corinne Fredouille, Anthony Larcher, Alexandre Preti, Gilles Pouchoulin, Nicholas Evans, Benoit Fauve, John Mason

This paper presents the ALIZE/SpkDet open source software packages for text independent speaker recognition. This software is based on the well-known UBM/GMM approach. It includes also the latest speaker recognition developments such as Latent Factor Analysis (LFA) and unsupervised adaptation. Discriminant classifiers such as SVM supervectors are also provided, linked with the Nuisance Attribute Projection (NAP). The software performance is demonstrated within the framework of the NISTÂ’06 SRE evaluation campaign. Several other applications like speaker diarization, embedded speaker recognition, password dependent speaker recognition and pathological voice assessment are also presented.