Voice imitation is mimicry of another speaker's voice characteristics and speech behavior. Professional voice mimicry can create entertaining, yet realistic sounding target speaker renditions. As mimicry tends to exaggerate prosodic, idiosyncratic and lexical behavior, it is unclear how modern spectral-feature automatic speaker verification systems respond to mimicry "attacks". We study the vulnerability of two well-known speaker recognition systems, traditional Gaussian mixture model . universal background model (GMM-UBM) and a state-of-the-art i-vector classifier with cosine scoring. The material consists of one professional Finnish imitator impersonating five well-known Finnish public figures. In a carefully controlled setting, mimicry attack does slightly increase the false acceptance rate for the i-vector system, but generally this is not alarmingly large in comparison to voice conversion or playback attacks.
Cite as: Hautamäki, R.G., Kinnunen, T., Hautamäki, V., Leino, T., Laukkanen, A.-M. (2013) I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. Proc. Interspeech 2013, 930-934, doi: 10.21437/Interspeech.2013-289
@inproceedings{hautamaki13_interspeech,
author={Rosa González Hautamäki and Tomi Kinnunen and Ville Hautamäki and Timo Leino and Anne-Maria Laukkanen},
title={{I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry}},
year=2013,
booktitle={Proc. Interspeech 2013},
pages={930--934},
doi={10.21437/Interspeech.2013-289}
}