First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Japanese Text-to-Speech Conversion System

Hiroki Kamanaka, Takashi Yazu, Keiichi Chihara, Makoto Morito

Human Interface Laboratory, OKI Electric Ind. Co., Ltd., Tokyo, Japan

This paper describes a newly developed Japanese text-to-speech conversion system. The phonetic and prosodic information for speech synthesis is extracted from the input text by the Japanese text analyzer so that Kanji and Kana texts can be input directly to the system. The synthetic speech is generated by concatenating speech synthesis units which contain symmetrical waveforms. As synthesis units, VCV syllables are used as well as CV syllables and symmetrical waveforms have been obtained by PSE analysis. Therefore, the synthetic speech sounds smooth and natural. The system has been built on a compact board which can be housed in a PC slot.

Full Paper

Bibliographic reference.  Kamanaka, Hiroki / Yazu, Takashi / Chihara, Keiichi / Morito, Makoto (1990): "Japanese text-to-speech conversion system", In ICSLP-1990, 789-792.