Hiroaki HATTORI
Text-Independent Speaker Recognition
Using Neural Networks
Abstract:This paper describes a text-independent speaker recognition method using predictive
neural networks. The speech production process is regarded as a non-linear process so
the speaker individuality in the speech signal also includes non-linearity. Therefore, the
predictive neural network, which is a non-linear prediction model based on multi-layer
perceptrons, is expected to be a more suitable model for representing speaker individuality. For text-independent speaker recognition, an ergodic model which allows transitions
to any other state, including self-transitions, is adopted as the speaker model and one
predictive neural network is assigned to each state. The proposed method was compared
to distortion based methods, HMM based methods, and a discriminative neural network
based method through a text-independent speaker recognition experiments on 24 female
speakers. The proposed method gave the highest recognition accuracy of 100.0%, and
the effectiveness of predictive neural networks for representing speaker individuality was
clarified.