Speaker verification based on fuzzy inference system with moving parametric consequents

This article presents an application of fuzzy nonlinear classifier to voice biometrics namely to speaker verification task. This classifier is closely related to a modification of a classical Takagi-Sugeno-Kang inference system and is based on a fuzzy moving consequents in If-Then rules. Good generalization properties of this classifier enahle to achieve low error rates even for short training speaker utterances. Achieved verification results are compared wit h the ones ohtained for the most popular in speaker recognition area techniques like Gaussian Mixture Models and vcctor quantization. All research is based on Polish speech corpus ROBOT designed for testing speech algorithms.