Designing Algorithms to Recognize Tones in Mandarin

Abstract

The Chinese language is a tonal language. The accuracy rate of Chinese speech recognition system will be affected directly by the accuracy rate of its tone recognition algorithm. The recognition problem of tones deserves a closer look if we want to build a highly reliable Chinese speech recognition system. In this paper, we studied the tone recognition problem in Mandarin. We have designed four features to distinguish the tones. We have also developed three major ways to classify tones. We have performed experiments to test the classification methods on large test samples (1390 syllables for each speaker with 19 speakers in total). The best classification method is the mixture on where we use the Euclidean distance on a multi-level decision tree. Its recognition rate is 89.35% for males and 80.90% for females of he mixture method. Individually, the recognition rate of the mixture method can reach higher than 90%. For one male the rates are 94.7%, 92.9%, 89.7%, 92.4% for tone 1 to tone 4.