Composite phoneme units for the speech synthesis of Japanese

Yoshinori Sagisaka*, Hirokazu Sato

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)


Japanese speech synthesis techniques based on composite phoneme units are surveyed. Japanese is an open-syllable language, and there are no consonant clusters in its phonemic system. Japanese is therefore structured with simple and basic syllables of a CV-type, and these are widely used in Japanese speech synthesis-by-rule instead of single phonemes. Other composite syllabic units such as VCV or CVC are also used in Japanese speech synthesis to achieve coarticulatory characteristics. In this paper, a speech synthesis method using CVC units with excitation waveform elements is described as an attempt to improve the quality of synthetic speech.

Original languageEnglish
Pages (from-to)217-223
Number of pages7
JournalSpeech Communication
Issue number2
Publication statusPublished - 1986 Jun
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Modelling and Simulation
  • Communication
  • Language and Linguistics
  • Linguistics and Language
  • Computer Vision and Pattern Recognition
  • Computer Science Applications


Dive into the research topics of 'Composite phoneme units for the speech synthesis of Japanese'. Together they form a unique fingerprint.

Cite this