Search

In this paper, a speaker verification algorithm, which is inspired by the physiology of hearing in the human auditory system, is proposed. The algorithm uses a modified self-organising map composed of spiking neurons. The architecture of the algorithm imitates the biomechanical mechanism of the human auditory system, which converts the speech signal from sound vibration waves into electrical spikes inside the cochlea. The paper also suggests a spike-based rank order coding input feature vector, which is designed to be representative of the real biological spike trains found within the human auditory nerve. During the training phase, the winner neuron in the proposed Spiking Self-Organising Map is updated only when its activity exceeds a specified threshold. The algorithm is evaluated using 50 speakers from the Centre for Spoken Language Understanding (CSLU2002) speaker verification database and shows a speaker verification performance of 90.1%. This compares favourably with previous non-spiking self-organising map that used Discrete Fourier Transform-based input feature vector with the same dataset. [ABSTRACT FROM AUTHOR]

This paper presents a multi-level speaker verification system that uses 64 discrete Fourier transform spectrum components as input feature vectors. A speech activity detection technique is used as a pre-processing stage to identify vowel phoneme boundaries within a speech sample. A modified self-organising map (SOM) is then used to filter the speech data by using cluster information extracted from three vowels for a claimed speaker. This SOM filtering stage also provides coarse speaker verification. Finally, a second speaker verification level of three multi-layer perceptron networks classifies the filtered frames provided by the SOMs. These multi-layer perceptrons work as fine-grained vowel-based speaker verifiers. The proposed verification algorithm shows a performance of 94.54% when evaluated using 50 speakers from the Centre for Spoken Language Understanding speaker verification database. In addition, it is shown that the novel discrete Fourier transform spectrum-based linear correlation pre-processing technique, presented here, provides the system with greater robustness against changes in speech volume levels when compared with an equivalent energy frame analysis. [ABSTRACT FROM AUTHOR]