Automatic voice recognition in open sets

Downloads

Authors

  • Czesław BASZTURA Institute of Telecommunication and Acoustics, Wrocław Technical University, Poland
  • Wojciech MAJEWSKI Institute of Telecommunication and Acoustics, Wrocław Technical University, Poland
  • Jerzy JURKIEWICZ Institute of Telecommunication and Acoustics, Wrocław Technical University, Poland

Abstract

Every system of automatic voice recognition can be divided into three parts: the voice source, the measuring system (the system of parameter extraction) and the classifier. The object of interest of the present paper is the classifier, in which emphasis is laid upon the procedure capable of recognizing voices in open sets. The methodology of investigations, analysis of the problem and the recognizing algorithm has been presented. Also the experimental results accounting for choice optimization and extraneous voice discrimination as well as the problem of choosing the threshold values for a given recognition strategy has been discussed.

References

[1] Cz. BASZTURA, Automatic speaker recognition by zero-crossing analysis of the speech signal, In: Speech Analysis and Synthesis (W. Jassem[ed.]), 5 PWN, p. 9-40, Warszawa 1980.

[2] Cz. BASZTURA, W. MAJEWSKI, The application of long-term analysis of the zero-crossing of a speech signal in automatic speaker identification, Arch. of Acoustics 3, 1, 3-15 (1978).

[3] Cz. BASZTURA, J. JURKIEWICZ, The zero-crossing analysis of a speech signal in the short-term method of automatic speaker identification, Arch. of Acoustics 3, 3, 185-196 (1978).

[4] J. Z. CYPKIN, Basics of the learning systems (in Polish) WNT, Warszawa 1973.

Most read articles by the same author(s)