论文信息 - An acoustic-phonetic oriented system for synthesizing Chinese

An acoustic-phonetic oriented system for synthesizing Chinese

Abstract The study of synthesizing Chinese is faced with the pressing task of improving sound quality. This article presents the structure and features of our synthesis system for Standard Chinese. This system was built on the basis of an acoustic-phonetic analysis of Chinese syllables. Several original models and rules are employed in the system. All the 1268 syllables in Standard Chinese have been synthesized by this system, which produces a sound quality close to that of natural speech with respect to both intelligibility and naturalness.

Yi Xu | Shun-an Yang

[1] Zhang Jialu. Acoustic parameters and phonological rules of a text-to-speech system for Chinese , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2] Gunnar Fant,et al. Acoustic Theory Of Speech Production , 1960 .

[3] Tai-Yi Huang,et al. A Chinese text-to-speech synthesis system based on an initial-final model , 1982, ICASSP.

[4] Dennis H. Klatt,et al. Software for a cascade/parallel formant synthesizer , 1980 .

[5] J. N. Holmes,et al. Formant synthesizers: Cascade or parallel? , 1983, Speech Commun..

[6] A. Rosenberg. Effect of glottal pulse shape on the quality of natural vowels. , 1969 .