INTERSPEECH 2007
8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Multi-Layer Kohonen Self-Organizing Feature Map for Language Identification

Liang Wang (1), Eliathamby Ambikairajah (1), Eric H. C. Choi (2)

(1) University of New South Wales, Australia
(2) NICTA, Australia

In this paper we describe a novel use of a multi-layer Kohonen self-organizing feature map (MLKSFM) for spoken language identification (LID). A normalized, segment-based input feature vector is used in order to maintain the temporal information of speech signal. The LID is performed by using different system configurations of the MLKSFM. Compared with a baseline PPRLM system, our novel system is capable of achieving a similar identification rate, but requires less training time and no phone labeling of training data. The MLKSFM with the sheet-shaped map and the hexagonal-lattice neighborhoods relationship is found to give the best performance for the LID task, and this system is able to achieve a LID rate of 76.4% and 62.4% for the 45-sec and 10-sec OGI speech utterances, respectively.

Full Paper

Bibliographic reference.  Wang, Liang / Ambikairajah, Eliathamby / Choi, Eric H. C. (2007): "Multi-layer kohonen self-organizing feature map for language identification", In INTERSPEECH-2007, 174-177.