Self-supervised pre-training with acoustic configurations for replay spoofing detection
share
Large datasets are well-known as a key to the recent advances in deep learning. However, dataset construction, especially for replay spoofing detection, requires the physical process of playing an utterance and re-recording it, which hinders the construction of large-scale datasets. To compensate for the limited availability of replay spoofing datasets, in this study, we propose a method for pre-training acoustic configurations using external data unrelated to replay attacks. Here, acoustic configurations refer to variables present in the process of a voice being uttered by a speaker and recorded through a microphone. Specifically, we select pairs of audio segments and train the network to determine whether the acoustic configurations of two segments are identical. We conducted experiments using the ASVspoof 2019 physical access dataset, and the results revealed that our proposed method reduced the relative error rate by over 37
READ FULL TEXT
