A comparisonal study of the multi-layer Kohonen self-organizing feature maps for spoken language identification

Our previous research indicates that the multi-layer Kohonen self-organizing feature map (MLKSFM) gives a promising performance for spoken language identification (LID). In this paper, we enhance this approach in two distinct ways. Firstly, by considering the phase information, we propose a new type of feature vector which combines the modified group delay function (MODGDF) and the traditional MFCC. Secondly, we propose a hierarchical structure of the MLKSFM, in which the pre-classification is performed at the lower level MLKSFM and the final language identification is performed at the top level MLKSFM. For the OGI-TS speech corpus, the best LID rate is achieved at 87.3% for the 45-sec test speech utterances by using the hierarchical MLKSFM with 4 classes pre-classified at the lower level MLKSFM. For the 10-sec test speech utterances, the best LID rated is achieved at 60.0% by using the non-hierarchical MLKSFM LID system.