Figure 7From: Homogenous ensemble phonotactic language recognition based on SVM supervector reconstructionPerformance of perturbational SVM supervector reconstruction subsystems. NIST LRE 2009, 30-s, HU frontend (EER and Cavg in percent). (a) Approach 1. (b) Approach 2. (c) Approach 3. (d) Approach 4.Back to article page