A Multi-Target Speaker Detection and Identification System Based on Combination of PLDA and DNN

Abstract

The paper describes a multi-target speaker detection and identification system based on a fusion of probabilistic linear discriminant analysis (PLDA) and deep neural network (DNN). PLDA is the state-of-the-art approach used in speaker recognition, thus we selected it as our baseline. We tried to develop a DNN based approach, that would be more accurate than the baseline, but only better discrimination between blacklist and background speakers was achieved. The fusion of PLDA and DNN improved performance of the baseline system.