• Computer Science
  • Published in INTERSPEECH 2004

Modeling phones coarticulation effects in a neural network based speech recognition system

@inproceedings{Ansary2004ModelingPC,
  title={Modeling phones coarticulation effects in a neural network based speech recognition system},
  author={Leila Ansary and Seyyed Ali Seyyed Salehi},
  booktitle={INTERSPEECH},
  year={2004}
}
In this paper we have designed and implemented speech recognition models in phone recognition level to model phones coarticulation effects. We have inspired these models from two human cognitive systems: neocortex and hippocampus. In the model inspired from the neocortex the first step is a primary and coarse classification of inputs, then model adapts itself to contexts extracted from these primary recognitions and we classify inputs again according to their extracted context. In the model… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-4 OF 4 CITATIONS

Improving pose manifold and virtual images using bidirectional neural networks in face recognition using single image per person

  • 2011 International Symposium on Artificial Intelligence and Signal Processing (AISP)
  • 2011
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Proposing two speaker adaptaion methods for deep neural network based speech recognition systems

  • 7'th International Symposium on Telecommunications (IST'2014)
  • 2014
VIEW 3 EXCERPTS
CITES RESULTS & METHODS

Effect of articulatory Δ and ΔΔ parameters on multilayer neural network based speech recognition

  • 2010 IEEE Asia Pacific Conference on Circuits and Systems
  • 2010
VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 11 REFERENCES

Cognitive maps and the hippocampus

  • Trends in Cognitive Sciences
  • 2003
VIEW 1 EXCERPT

Context-dependent acoustic modeling using graphemes for large vocabulary speech recognition

  • 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 2002
VIEW 2 EXCERPTS

Improvement on Representation Parameters Extraction Methods in Speech Recognition Systems", MS Thesis, Amirkabir University of Technology, Biomedical department

M. Rahiminejad
  • 2002
VIEW 2 EXCERPTS

Context modeling in a hybrid HMM-neural net speech recognition system

  • Proceedings of International Conference on Neural Networks (ICNN'97)
  • 1997
VIEW 1 EXCERPT

Farsi Continuous speech recognition using human brain functions in speech perception

S. A. Seyyed Salehi
  • PhD thesis,
  • 1996
VIEW 1 EXCERPT

An Application of Recurrent Neural Networks to Phone Probability Estimation

A J.Robinson
  • IEEE Trans. Neural Networks,
  • 1994
VIEW 1 EXCERPT