Speech recognition using recurrent neural prediction model

  title={Speech recognition using recurrent neural prediction model},
  author={Toru Uchiyama and Haruhisa Takahashi},
  journal={Systems and Computers in Japan},
The neural prediction model (NPM) proposed by Iso and Watanabe is a successful example of a speech recognition neural network with a high recognition rate. This model uses multilayer perceptrons for pattern prediction (not for pattern recognition), and achieves a recognition rate as high as 99.8% for speaker-independent isolated words. This paper proposes a recurrent neural prediction model (RNPM), and a recurrent network architecture for this model. The proposed model very significantly… CONTINUE READING
2 Citations
16 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 16 references

Speaker-independent speech recognition using a neural prediction model

  • K Iso, T. Watanabe
  • Trans IEICE 1990;J73-D-II:1315–1321
  • 1990
Highly Influential
4 Excerpts

Voice data processing using neural network; Bit: Neural Systems 1989;21:183–195

  • S. Nakagawa
  • He is a member of the International Neural…
  • 1984
Highly Influential
10 Excerpts

Continuous voice recognition using recurrent network

  • N Yanagitani, H Takahashi, E Tomita
  • Tech Rep IEIC
  • 1993

Continuous voice recognition using recurrent network. Tech Rep IEIC 1993;SP93-111

  • N Yanagitani, H Takahashi, E. Tomita
  • 1993
1 Excerpt

Natural language interface with context using connectionist model

  • Utumi, Hori, Ohsuka
  • J Artif Intell
  • 1992
1 Excerpt

Learning algorithm of recurrent network

  • K Doya
  • Measurement and Control
  • 1991

Learning algorithm of recurrent network. Measurement and Control 1991;30:296–301

  • K. Doya
  • 1991
1 Excerpt

Voice recognition using sequential neural network

  • S Nakagawa
  • Trans IEICE
  • 1991

Similar Papers

Loading similar papers…