A COMPARISON OF NEURAL NET AND LINEAR CLASSIFIER AS THE PATTERN RECOGNIZER IN AUTOMATIC LANGUAGE IDENTIFICATION

The goal for language identiication (LID) is to quickly and accurately identify the language being spoken in a given test utterance. Recent researches has shown the importance of acoustic, phonotactic and prosodic information for language identiication. How to combine these multiple information sources to give the nal results is still a research issue. Traditional ways to combine multiple scores were similar to a linear classiier. In this paper, experiments were conducted to compare the performance of linear classiier based and neural network based nal score combination. The results showed that approximately 15% errors of linear classiier based system were reduced by the neural network based system, which suggests that a non-linear combination of multi-information sources is necessary for language identiication.