Speaker identification by computer and human evaluated on the SPIDRE corpus

Closed set speaker identification experiments were performed on a SPIDRE subset of the switchboard corpus with matched and mismatched telephone handset conditions. The impact of mismatched and matched conditions was evaluated. The tested conversations were divided into fixed block lengths of 10 ms. It was found that the confusion between speakers was mainly due to the strong telephone handset influence.

[1]  G.R. Doddington,et al.  Speaker recognition—Identifying people by their voices , 1985, Proceedings of the IEEE.

[2]  Li Liu,et al.  Speaker identification using hybrid LVQ-SLP networks , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[3]  Douglas A. Reynolds,et al.  Measuring fine structure in speech: application to speaker identification , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.