Improvement of Accent Sandhi Rules Based on Japanese Accent Dictionaries

  • Hiroto Aoyama
  • Takashi Nose
  • Yuya Chiba
  • Akinori ItoEmail author
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 110)


In order to synthesize more natural speech with Japanese text-to-speech systems, we improve accent sandhi rules. The conventional Japanese accent sandhi rules lack rules related to numerals and counter words in conventional rules. In this paper, we comprehensively improved the accent sandhi rules as well as those related to numerals and counter words, concerning accent rules related to word combinations described in the Japanese accent dictionaries. Then, accent estimation experiments were conducted using the conventional and improved rules to evaluate the accuracy of the estimation by the two types of rules. The effectiveness and problems of the accent sandhi rules themselves and improved rules were discussed by analyzing the experimental results.


Text-to-speech Accent sandhi rules Numerals Counter words Accent dictionary 


  1. 1.
    Sagisaka, Y., Sato, H.: Accentuation rules for Japanese word concatenation. IECE Trans. Jpn. 66D(7), 849–856 (1983). (in Japanese)Google Scholar
  2. 2.
  3. 3.
    Akinaga, K. (ed.): Shinmeikai Japanese Accent Dictionary with CD. Sanseido (2010) (in Japanese)Google Scholar
  4. 4.
    NHK Broadcasting Culture Research Institute (ed.): NHK’s New Dictionary of Japanese Pronunciation and Accentuation. NHK Publishing (2016) (in Japanese)Google Scholar
  5. 5.
    Kuroiwa, R., Minematsu, N., Hirose, K.: Improvement of accent sandhi rules for Japanese TTS systems. In: Proceeding Autumn Meeting of the Acoustic Society of Japan, pp. 427–428 (2005) (in Japanese)Google Scholar
  6. 6.
    Suzuki, M., Kuroiwa, R., Innami, K., Kobayashi, S., Shimizu, S., Minematsu, N., Hirose, K.: Accent sandhi estimation of Tokyo dialect of Japanese using CRF. In: Proceeding Autumn Meeting of the Acoustic Society of Japan, pp. 299–302 (2012) (in Japanese)Google Scholar
  7. 7.
    JNAS: Japanese Newspaper Article Sentences.
  8. 8.
    MeCab: Yet Another Part-of-Speech and Morphological Analyzer.
  9. 9.
    NAIST Japanese Dictionary Project.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Hiroto Aoyama
    • 1
  • Takashi Nose
    • 1
  • Yuya Chiba
    • 1
  • Akinori Ito
    • 1
    Email author
  1. 1.Tohoku UniversitySendaiJapan

Personalised recommendations