Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Imposture Using Synthetic Speech Against Speaker Verification Based on Spectrum and Pitch
Takashi Masuko (1), Keiichi Tokuda (2), Takao Kobayashi (1)
(1) Interdisciplinary Graduate School of Science and Engineering,
Tokyo Institute of Technology, Yokohama, Japan
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.
(2) Department of Computer Science,
Nagoya Institute of Technology, Japan
Masuko, Takashi / Tokuda, Keiichi / Kobayashi, Takao (2000):
"Imposture using synthetic speech against speaker verification based on spectrum and pitch",
In ICSLP-2000, vol.2, 302-305.