A Novel Method for Automatic Tonal and Non-Tonal Language Classification

This paper describes a novel method for tonal and non-tonal language classification using prosodic information. Normalized feature parameters that measure the speed and level of pitch change are used to perform the classification task. To demonstrate the effectiveness of the proposed method, the classification rates of different system configurations are compared. Evaluating a 16-language classification task using a GMM classifier, the novel system can achieve a classification rate of 87.1% for 45-sec speech segments and 81.9% for 10-sec speech segments. Possible applications of the new method to perform pre-classification in language identification are also discussed.