MERGING CLASSIFIER DECISIONS FOR SPEAKER RECOGNITION
The paper proposes using fuzzy integrals for merging classifier decisions in speaker recognitionsystems. Instantaneous frequency and instantaneous amplitude are considered as the set of features. The approach shows significantly better results than a single classifier. A comparison of the proposed a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
2016-09-01
|
| Series: | Informatika |
| Online Access: | https://inf.grid.by/jour/article/view/3 |