基于ResNet的伪造语音鉴别研究

he anti-spoofing methods in existing Automatic Speaker Verification (ASV) systems still have insufficient generalizability when facing unseen attacks. The Res2Net approach designs a residual-like connection between feature groups within one block, which increases the possible receptive fields and improves the system\'s detection generalizability. However, such a residual-like connection is performed by a direct addition between feature groups without channelwise priority. The information across channels may not contribute to spoofing cues equally, and the less relevant channels are expected to be suppressed before adding onto the next feature group, so that the system can generalize better to unseen attacks. Based on this, this paper proposes a novel channel-wise gated Res2Net, which modifies Res2Net to enable a channel-wise gating mechanism in the connection between feature groups, and verifies the effectiveness of the method through experimental results on the ASVspoof 2019 Logical Access (LA) dataset.