Language identification using MLKSFM for pre-classification with novel front-end features

This paper presents two novel contributions to automatic language identification. The first one is the use of the modified multi-layer Kohonen self-organizing feature map (MLKSFM) as a pre-classification for language identification (LID). Secondly, we discuss the novel application of empirical mode decomposition (EMD) to generate features for the LID pre-classification task. The use of instantaneous frequency (IF) and instantaneous amplitude (IA) of a speech signal as features for the pre-classifier is investigated. The experiment results on a 16-language speech database indicates that, the EMD by itself cannot perform well in the LID task, however it helps to improve the pre-classification rate when concatenated with other cepstral features. The overall LID performance is also increased when pre-classification is applied. We achieve LID rates of 85.2% and 62.3% for 45-sec and 10-sec test utterances, respectively.