@article{oai:ipsj.ixsq.nii.ac.jp:00210370,
 author = {Ryoya, Yaguchi and Sayaka, Shiota and Nobutaka, Ono and Hitoshi, Kiya and Ryoya, Yaguchi and Sayaka, Shiota and Nobutaka, Ono and Hitoshi, Kiya},
 issue = {3},
 journal = {情報処理学会論文誌},
 month = {Mar},
 note = {In this paper, we propose a replay attack detection (RAD) method that uses spatial and spectral features of a stereo signal. To distinguish genuine and replayed utterance, we focus on non-speech segments, in which a human does not emit sound, but a loudspeaker for replay attack might emit some recorded noise or its electromagnetic noise. The generalized cross-correlation (GCC) based spatial features capture this difference. To improve the robustness against the variety of recording environments, we combine the spatial features with spectral features. In particular, we fuse the output scores of GCC-based and spectral feature-based methods. In experiments, we confirm the effectiveness of the combination of spatial and spectral features.
------------------------------
This is a preprint of an article intended for publication Journal of
Information Processing(JIP). This preprint should not be cited. This
article should be cited as: Journal of Information Processing Vol.29(2021) (online)
DOI　http://dx.doi.org/10.2197/ipsjjip.29.275
------------------------------, In this paper, we propose a replay attack detection (RAD) method that uses spatial and spectral features of a stereo signal. To distinguish genuine and replayed utterance, we focus on non-speech segments, in which a human does not emit sound, but a loudspeaker for replay attack might emit some recorded noise or its electromagnetic noise. The generalized cross-correlation (GCC) based spatial features capture this difference. To improve the robustness against the variety of recording environments, we combine the spatial features with spectral features. In particular, we fuse the output scores of GCC-based and spectral feature-based methods. In experiments, we confirm the effectiveness of the combination of spatial and spectral features.
------------------------------
This is a preprint of an article intended for publication Journal of
Information Processing(JIP). This preprint should not be cited. This
article should be cited as: Journal of Information Processing Vol.29(2021) (online)
DOI　http://dx.doi.org/10.2197/ipsjjip.29.275
------------------------------},
 title = {Replay Attack Detection Based on Spatial and Spectral Features of Stereo Signal},
 volume = {62},
 year = {2021}
}