Feature mapping and recuperation by using elliptical basis function networks for robust speaker verification

Abstract

The performance of speaker verification systems is often compromised under real-world environments. For example, variations in handset characteristics could cause severe performance degradation. This paper presents a novel method to overcome this problem by using a non-linear handset mapper. Under this method, a mapper is constructed by training an elliptical basis function network using distorted speech features as inputs and the corresponding clean features as the desired outputs. During feature recuperation, clean features are recovered by feeding the distorted features to the feature mapper. The recovered features are then presented to a speaker model as if they were derived from clean speech. Experimental evaluations based on 258 speakers of the TIMIT and NTIMIT corpuses suggest that the feature mappers improve the verification performance remarkably.

Surrogating for High Dimensional Computationally Expensive Multi-Modal Functions with Elliptical Basis Function Models

“…Since the amplitude variation of test functions are not uniform in the global scope, it's not appropriate to sample points in the complex shape of the surface uniform directly. We adopt uniform sampling points to test the approximation of the model, add the maximum sampling error points into sample space, update the surrogate model and error analysis sample and fully exploit the performance of RBF-NN and EBF-NN [7].…”