A Japanese TTS system based on multiform units and a speech modification algorithm with harmonics reconstruction

Satoshi Takano, Kimihito Tanaka, Hideyuki Mizuno, Masanobu Abe

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)


This paper proposes a new lext-to-speech (TTS) system that utilizes large numbers of speech segments to produce very natural and intelligible synthetic speech. There are two innovations; new multiform synthesis units and a new speech modification algorithm based on a vocoder that offers harmonics reconstruction. The multiform units make it possible to reduce acoustic discontinuities at concatenation points and unnatural sound by preparing synthesis units with various lengths and various Fo contours. The new speech modification algorithm, on the other hand, improves the quality of prosody modified speech. This algorithm is extremely effective in synthesizing speech whose prosodic parameters are quite different from those of synthesis units. Listening tests confirm that the new synthesis units yield speech with high intelligibility and naturalness, and that the new speech modification algorithm is superior to all other conventional vocoders and waveform domain algorithms including TD-PSOLA, especially when modifying the Fo frequency upward.

Original languageEnglish
Pages (from-to)3-10
Number of pages8
JournalIEEE Transactions on Speech and Audio Processing
Issue number1
Publication statusPublished - 2001
Externally publishedYes


  • Evaluation of synthesis technique and systems
  • Segmentai units and adjustment rules
  • Spectral analysis
  • Synthesis structure and systems

ASJC Scopus subject areas

  • Software
  • Acoustics and Ultrasonics
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering


Dive into the research topics of 'A Japanese TTS system based on multiform units and a speech modification algorithm with harmonics reconstruction'. Together they form a unique fingerprint.

Cite this