Language Recognition in iVectors Space

Abstract

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 stateof-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.

8 Figures and Tables

020402011201220132014201520162017
Citations per Year

164 Citations

Semantic Scholar estimates that this publication has 164 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Gonzlez2011LanguageRI, title={Language Recognition in iVectors Space}, author={David Mart{\'i}nez Gonz{\'a}lez and Oldrich Plchot and Luk{\'a}s Burget and Ondrej Glembek and Pavel Matejka}, booktitle={INTERSPEECH}, year={2011} }