Pattern-matching for speaker verification: A review

Abstract

This paper presents a brief survey on Pattern matching for speaker verification. Pattern matching performed for Speaker Verification (SV), is the process of verifying the claimed identity of a registered speaker by using their voice characteristics and further subdivided into text-dependent and textindependent. Paper outlines various models performance levels and the work undertaken by the researchers. It has been viewed over as, among these models GMM comparatively performs better and this paper is beneficial for researchers to proceed over in their work.