Skip to main content

Part of the book series: NATO ASI Series ((NATO ASI F,volume 46))

Abstract

In this paper we introduce a new generalization of the Generalized Linear Discriminant Function, in which the dimension of the representation space depends on the class. This generalization is applied to Speech Recognition with Difficult Dictionaries, leading to a (preliminary) error rate reduction over 50% with respect to the standard approach.

Work partially supported by grant No. PA85-0086 of the Spanish CAICYT.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. E.L. Bocchieri; G.R. Doddington: “Frame-Specific Statistical Features for Speaker Independent Speech Recognition” IEEE Trans, on Acoust. Speech and Signal Proc. Vol. 34 (4), pp. 755–764 (1986)

    Article  Google Scholar 

  2. F.J. Corell; J.C. Tabarés; E. Vidal; F. Casacuberta: “Utilización de Funciones Discriminantes Lineales Generalizadas en el Reconocimiento de Palabras Aisladas con Ciertos Diccionarios Difíciles” To appear in Qüestió.

    Google Scholar 

  3. R.O. Duda; P.E. Hart: “Pattern Classification and Scene Analysis”. J. Wiley. (1973)

    Google Scholar 

  4. A. Fernandez; P. Rodriguez; E. Vidal; H. Rulot: “Reconocimiento de Palabras muy Semejantes basado en la Minimización del Criterio Perceptron” To be appear in Revista de Informática y Automática.

    Google Scholar 

  5. R.K. Moore; M.J. Russell; M.J. Tomlinson: “Locally Constrained Dynamic Programming in Automatic Speech Recognition” Proc. or the ICASSP- 82, pp. 1270–1273 (1982)

    Google Scholar 

  6. R.K. Moore; M.J. Russell; M.J. Tomlinson: “The Discriminative Network: A Mechanism for focusing Recognition in Whole-Word Pattern Recognition” Proc. of the ICASSP-83, pp. 1041–1044 (1983)

    Google Scholar 

  7. L.R. Rabinerf; J.G. Wilpon: “Isolated Word Recognition using a Two-Pass Pattern Recognition Approach”. Proc. of the ICASSP-81, pp. 724- 727. (1981)

    Google Scholar 

  8. E. Vidal; F. Casacuberta; H. Rulot: “Is the DIW “Distance” really a Metric?: An Algorithm reducing the Number of DIW comparisons in Isolated Word Recognition”. Speech Communication. Vol (4), pp. 333–344 (1985)

    Article  Google Scholar 

  9. E. Vidal; F. Casacuberta: “Variable Dimension Generalized Linear Discriminant Functions and Applications”. To be published.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1988 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Casacuberta, F., Vidal, E. (1988). Speech Recognition With Difficult Dictionaries. In: Niemann, H., Lang, M., Sagerer, G. (eds) Recent Advances in Speech Understanding and Dialog Systems. NATO ASI Series, vol 46. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83476-9_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-83476-9_26

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-83478-3

  • Online ISBN: 978-3-642-83476-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics