Odyssey 2012

The Speaker and Language Recognition Workshop

Speaker Vectors from Subspace Gaussian Mixture Model as Complementary Features for Language Identification

Presented by:
Oldrich Plchot
Author(s):
Oldrich Plchot, Martin Karafiat, Niko Brummer, Ondrej Glembek, Pavel Matejka, Edward de Villiers and Jan Cernocky

In this paper, we explore new high-level features for language identification. The recently introduced Subspace Gaussian Mixture Models (SGMM) provide an elegant and efficient way for GMM acoustic modelling, with mean supervectors represented in a low-dimensional representative subspace. SGMMs also provide an efficient way of speaker adaptation by means of low-dimensional vectors. In our framework, these vectors are used as features for language identification. They are compared with our acoustic iVector system, which is currently considered state-of-the-art for Language Identification and Speaker Verification. The results of both systems and their fusion are reported on the NIST LRE2009 dataset.