Abstract
Nowadays a big research effort is being made in the development of CSR systems, both ANN-based and HMM-based. Up to now, the HMM-based systems seem to have the best performance, although the ANN-based ones are being developed quicker than the HMM-based due to the new topologies that are being tested with increasingly good results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J. S. Bridle, “Alpha-Nets: A Recurrent ‘Neural’ Network Architecture with a Hidden Markov Model Interpretation,” Speech Communications, Vol. 9, pp. 83–92, 1990.
J. Díaz, “A new neuron model foran Alphanet-Semicontinuous HMM,” Proc. ICASSP′93, Vol. 1, pp. 529–532, 1993.
J. C. Segura, “Modelos de Markov con Cuantización Dependiente para Reconocimiento de Voz,” Dept. de Electrónica y Tecnología de Computadores. Universidad de Granada, Doctoral Thesis, November 1991.
H. Ney, “Improvements in beam search for 10.000-word continuous speech recognizer,” Proc. ICASSP′92, Vol. 1, pp. 9–12, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Segura-Luna, J.C., Díaz-Verdejo, J.E., Rubio-Ayuso, A.J., García-Teodoro, P., López-Soler, J.M. (1995). SLHMM: An ANN Approach for Continuous Speech Recognition. In: Ayuso, A.J.R., Soler, J.M.L. (eds) Speech Recognition and Coding. NATO ASI Series, vol 147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-57745-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive