INTERSPEECH 2011
12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Language Recognition in iVectors Space

David Martínez (1), Oldřich Plchot (2), Lukáš Burget (2), Ondřej Glembek (2), Pavel Matějka (2)

(1) Universidad de Zaragoza, Spain
(2) Brno University of Technology, Czech Republic

The concept of so called iVectors, where each utterance is represented by fixed-length low-dimensional feature vector, has recently become very successfully in speaker verification. In this work, we apply the same idea in the context of Language Recognition (LR). To recognize language in the iVector space, we experiment with three different linear classifiers: one based on a generative model, where classes are modeled by Gaussian distributions with shared covariance matrix, and two discriminative classifiers, namely linear Support Vector Machine and Logistic Regression. The tests were performed on the NIST LRE 2009 dataset and the results were compared with state-of-the-art LR based on Joint Factor Analysis (JFA). While the iVector system offers better performance, it also seems to be complementary to JFA, as their fusion shows another improvement.

Full Paper

Bibliographic reference.  Martínez, David / Plchot, Oldřich / Burget, Lukáš / Glembek, Ondřej / Matějka, Pavel (2011): "Language recognition in ivectors space", In INTERSPEECH-2011, 861-864.