LGApr 2, 2019
Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural NetworksStefano Imoscopi, Volodya Grancharov, Sigurdur Sverrisson et al.
This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.