Sixth International Conference on Spoken Language Processing
This paper presents recent development on text-dependent speaker verification technology in EU project PICASSO, which have improved the SV performance significantly. In the project we adopt HMM approach for pattern matching. In the paper we describes four different techniques, adaptive variance flooring, multiple use of enrolment sample, generalised competitive measurement for score normalisation and hybrid method for score normalisation to improve HMM method for speaker verification. The evaluation results are given for each of these techniques.
Bibliographic reference. Gu, Yong / Thomas, Trevor (2000): "Advances on HMM-based text-dependent speaker verification", In ICSLP-2000, vol.3, 993-996.