Feature fusion based on auditory and speech systems for an improved voice biometrics system using artificial neural network

Abstract

In today's world, identifying a speaker has become an essential task. Especially for systems that rely on voice commands or speech in general to operate. These systems use speaker-specific features to identify the individual, features such as Mel Frequency Cepstral Coefficients, Linear Predictive Coding, or Perceptual Linear Predictive. Although these features provide different representations of speech, they can all be considered as either auditory system based (type 1) or speech system based (type 2). In this work, a method of improving existing voice biometrics system is presented. Fusing a type 1 feature with a type 2 feature is evaluated and an artificial neural network is trained and tested on in-campus recorded data set. The results confirm the ability for such an approach to be utilized for improving voice biometrics system, regardless of the underlying task being speaker identification or verification