This paper describes security of speaker verification systems against imposture using synthetic speech. We propose a text-prompted speaker verification technique which utilizes pitch information in addition to spectral information, and investigate whether synthetic speech is rejected. Experimental results show that pitch information is not necessarily useful for rejection of synthetic speech, and it is required to develop techniques to discriminate synthetic speech from natural speech.
Cite as: Masuko, T., Tokuda, K., Kobayashi, T. (2000) Imposture using synthetic speech against speaker verification based on spectrum and pitch. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 302-305, doi: 10.21437/ICSLP.2000-269
@inproceedings{masuko00_icslp,
author={Takashi Masuko and Keiichi Tokuda and Takao Kobayashi},
title={{Imposture using synthetic speech against speaker verification based on spectrum and pitch}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 2, 302-305},
doi={10.21437/ICSLP.2000-269}
}