First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Mandarin Speech Synthesis by the Unit of Coarticulatory Demi-syllable

Chi-Shi Liu (1,2), Wern-Jun Wang (1), Shiow-Min Yu (1), Hsiao-Chuan Wang (2)

(1) Telecommunication Laboratories, Ministry of Communication, Chung-Li, Taiwan
(2) Department of Electrical Engineering, Nationalising Hua University, Taiwan

In this paper, we will discuss the selection of synthesis unit for Mandarin speech synthesis. To choose the synthesis unit which could be easily segmented and concatenated, and produce natural and intelligent speech, we proposed the synthesis unit of Coarticulatory Demi-syllable segmented from di-syllable words. We found that spectral continuity of concatenating demisyllable still kept good. By subjectively listening, testers felt that the Coarticulatory Demi-syllable produced more natural and intelligent synthetic speech than monosyllable, but less than synthesis-by-analysis speech.

Full Paper

Bibliographic reference.  Liu, Chi-Shi / Wang, Wern-Jun / Yu, Shiow-Min / Wang, Hsiao-Chuan (1990): "Mandarin speech synthesis by the unit of coarticulatory demi-syllable", In ICSLP-1990, 781-784.