Exploring universal speech attributes for speaker verification

Abstract

The universal speech attributes for speaker verification (SV) are addressed in this paper. The aim of this work is to exploit fundamental characteristics across different speakers within the deep neural network (DNN)/i-vector framework. The manner and place of articulation form the fundamental speech attribute unit inventory, and new attribute units for acoustic modelling are generated by a two-step automatic clustering method in this paper. The DNN based on universal attribute units is used to generate posterior probability in total variability modelling and i-vector extracting for the speaker recognition procedure. Furthermore, Gaussian mixture models (GMMs) are used to fit the distribution of the features associated with a given context-dependent attribute unit to improve performance. The experiments are carried out on the core test from the NIST SRE 2008 corpus; the proposed system can obtain better performance than all other state-of-the-art systems.