EPFL
 Biomedical Imaging GroupSTI
EPFL
  Publications
English only   BIG > Publications > Speaker Recognition


 CONTENTS
 Home Page
 News & Events
 People
 Publications
 Tutorials and Reviews
 Research
 Demos
 Download Algorithms

 DOWNLOAD
 PDF
 Postscript
 All BibTeX References

A Residue-Based Approach to Text-Independent Speaker Recognition

P. Thévenaz, H. Hügli

Proceedings of the First Swiss Symposium on Pattern Recognition and Computer Vision, Lausanne VD, Swiss Confederation, January 30-31, 1992, pp. 35-41.



The subject of this paper is speaker recognition, which aims at asserting the identity of people on the basis of their voice only. Several techniques are already available; our contribution is to be found in the investigation of features new to this domain, named residue of the linear predictive coding analysis. Our experiments in text-independent mode show that the results obtained by using these features are as good as those obtained by some other classical technique making use of the pitch, while requiring less fine tuning of parameters; hence they can be considered more appealing, because of a more direct implementation.


@INPROCEEDINGS(http://bigwww.epfl.ch/publications/thevenaz9201.html,
AUTHOR="Th{\'{e}}venaz, P. and H{\"{u}}gli, H.",
TITLE="A Residue-Based Approach to Text-Independent Speaker
        Recognition",
BOOKTITLE="Proceedings of the First Swiss Symposium on Pattern
        Recognition and Computer Vision",
YEAR="1992",
editor="",
volume="",
series="",
pages="35--41",
address="Lausanne VD, Swiss Confederation",
month="January 30-31,",
organization="",
publisher="",
note="")

© 1992 SAPR. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from SAPR.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.