QUALITY BASED SPEAKER VERIFICATION SYSTEMS USING FUZZY INFERENCE FUSION SCHEME

摘要

Performances of single biometric speaker verification systems are outstanding in clean condition but drop significantly in noisy condition. Implementation of multibiometric systems is one of the solutions to this limitation. However, in order to ensure the performances of multibiometric systems are sustained, the optimum weight for the fusion system must be determined correctly according to the quality of current data. This study proposes the use of Fuzzy Inference System for weight inference. Two traits i.e., speech and lip are used while Support Vector Machine (SVM) is employed as the classifier in this study. The speech features are extracted using the Mel Frequency Cepstrum Coefficient (MFCC) method and the lip features are extracted using Region of Interest (ROI) method. The performances of single modal system (i.e., speech and lip) and multibiometric systems with sugeno and mamdani approaches are compared at different quality conditions in this study. Experimental results prove that the use of Fuzzy Inference System as weight inference is a very promising approach. For 15 dB SNR speech signal and 0.2 lip quality density, the GAR performances at FAR equals 0.1% for Mamdani-type, Sugeno-type, lip and speech systems are observed as 94, 95, 86 and 7%, respectively. In short, the proposed fusion scheme based on Fuzzy logic is able to maintain the performance of fusion system especially when one of the biometric sources is in noisy condition due to its capability to infer the correct fusion weight according to current data quality.