Automatic generation of multiple pronunciations based on neural networks

Toshiaki Fukada*, Takayoshi Yoshimura, Yoshinori Sagisaka

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

31 Citations (Scopus)


We propose a method for automatically generating a pronunciation dictionary based on a pronunciation neural network that can predict plausible pronunciations (realized pronunciations) from the canonical pronunciation. This method can generate multiple forms of realized pronunciations using the pronunciation network. For generating a sophisticated realized pronunciation dictionary, two techniques are described: (1) realized pronunciations with likelihoods and (2) realized pronunciations for word boundary phonemes. Experimental results on spontaneous speech show that the automatically derived pronunciation dictionaries give consistently higher recognition rates than a conventional dictionary.

Original languageEnglish
Pages (from-to)63-73
Number of pages11
JournalSpeech Communication
Issue number1
Publication statusPublished - 1999
Externally publishedYes


  • Neural networks
  • Pronunciation dictionary
  • Speech recognition
  • Spontaneous speech

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 'Automatic generation of multiple pronunciations based on neural networks'. Together they form a unique fingerprint.

Cite this