Abstract
Most techniques for speaker verification today use Gaussian Mixture Models (GMMs) and make the decision by comparing the likelihood of the speaker model to the likelihood of a universal background model (UBM). The paper proposes to replace the UBM by an individual background model (IBM) that is generated for each speaker. The IBM is created using the K-nearest cohort models and the UBM by a simple new adaptation algorithm. The new GMM-IBM speaker verification system can also be combined with various score normalization techniques that have been proposed to increase the robustness of the GMM-UBM system. Comparative experiments were held on the NIST-2004-SRE database with a plain system setting (without score normalization) and also with the combination of adaptive test normalization (ATnorm). Results indicated that the proposed GMM-IBM system outperforms a comparable GMM-UBM system.
| Original language | English |
|---|---|
| Pages (from-to) | 1271-1274 |
| Number of pages | 4 |
| Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
| State | Published - 2009 |
| Event | 10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom Duration: 6 Sep 2009 → 10 Sep 2009 |
Keywords
- Cohort selection
- Gaussian mixture models
- Kullback-Leibler divergence
- Model adaptation
- Score normalization
- Speaker verification