Learning the decision function for speaker verification
Authors:
- S. BengioSBS. Bengio
- J. MariethozJMJ. Mariethoz
- 13 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 425-428
Abstract
This paper explores the possibility to replace the usual thresh- olding decision rule of log likelihood ratios used in speaker verification systems by more complex and discriminant de- cision functions based for instance on Linear Regression models or Support Vector Machines. Current speaker verifi- cation systems, based on generative models such as HMMs or GMMs, can indeed easily be adapted to use such decision functions. Experiments on both text dependent and text in- dependent tasks always yielded performance improvements and sometimes significantly.Keywords
This publication has 4 references indexed in Scilit:
- Robust methods of updating model and a priori threshold in speaker verification2002
- A comparison of a priori threshold setting procedures for speaker verification in the CAVE project2002
- A Tutorial on Support Vector Machines for Pattern RecognitionData Mining and Knowledge Discovery, 1998
- The Nature of Statistical Learning Theory1995