Advertisement

On the Use of Recurrent Neural Networks for Grammar Learning and Word Spotting

  • Jorge Alvarez Cercadillo
  • Luis A. Hernández Gómez
Conference paper
Part of the NATO ASI Series book series (volume 147)

Abstract

In this work we try to infer from the speech all the possible sequences of allophones and their distribution over time by using a recursive network architecture, in which its recurrent connections learn phoneme sequence relationships. We describe some experiments in the context of Keyword Spotting.

Keywords

Hide Markov Model Recurrent Neural Network Word Level Grammatical Inference Phoneme Sequence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Wilpon et al. Automatic Recognition of Keywords in Unconstrained Speech Using Hidden Markov Models. IEEE Tans. on ASSP, Vol. 38, No. 11, 1870–1878, Nov. 1990CrossRefGoogle Scholar
  2. [2]
    R. Rose, D. Paul. A Hidden Markov Model Based Keyword Recognition System. Proc ICASSP 90, pp. 129–132Google Scholar
  3. [3]
    C.H. Lee, L.R. Rabiner, R. Pieraccini and J.G Wilpon. Acoustic modeling for large vocabulary speech recognition. Computer Speech and Language, pp. 127–165, 1990Google Scholar
  4. [4]
    Rabiner et al. On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition. Bell System Tech J., Vol. 62, No 4, 1075–1105, April, 1983MathSciNetGoogle Scholar
  5. [5]
    A.W. Smith and D. Zipser. Encoding sequential structure: Experience with the real-time recurrent learning algorithm. Proc. IJCNN, Vol. I, pp. 525–532, June 1989Google Scholar
  6. [6]
    Y.D. Liu, et al. Grammatical inference and neural network state machines. Proc IJCNN, Vol. I, pp. 285–288, January 1990Google Scholar
  7. [7]
    Morgan and Scofield. Neural Networks and Speech Processing; pp. 264–273. Kluwer Academic Publishers, 1991Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Jorge Alvarez Cercadillo
    • 1
  • Luis A. Hernández Gómez
  1. 1.Universidad Politécnica de Madrid. Dpto. SSR, ETSI Telecomunicación, UPMCiudad Universitaria s/nMadridSPAIN

Personalised recommendations