A Method of Part of Speech Based on the Algorithm of C4.5 for Polyphone

Chinese is one of graceful languages, not only it´s hieroglyphic writing, but also one of flexible languages, which can describe a thing or sensation of people visually. This is because of polyphone, which exists in Chinese. But it´s also because of polyphone, there are some difficult in Chinese speech synthesis, especially in the conversion between character and pronunciation. Polyphone is a large proportion in Chinese, so the problem of polyphone is the key in the module of character-pronunciation conversion. In this paper, the part of speech rules is presented to solve the problem of polyphone, which is based on the algorithm of C4.5. And experiment results presented to prove the effectiveness of this method.