End-to-End anti-spoofing with RawNet2

By Hemlata Tak, Jose Patino, Massimiliano Todisco, Andreas Nautsch, N. Evans, Anthony Larcher. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020

551 citations recorded by the source corpus.

Spoofing countermeasures aim to protect automatic speaker verification systems from being manipulated by spoofed speech signals. While results from the most recent ASVspoof 2019 evaluation show great potential to detect most forms of attack, some continue to evade detection. This paper reports the first application of RawNet2 to anti-spoofing. RawNet2 ingests raw audio and has potential to learn cues that are not detectable using more traditional countermeasure solutions. We describe modifications made to the original RawNet2 architecture so that it can be applied to anti-spoofing. For A17 attacks, our RawNet2 systems results are the second-best reported, while the fusion of RawNet2 and baseline countermeasures gives the second-best results reported for the full ASVspoof 2019 logical access condition. Our results are reproducible with open source software.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/722827f8adafb61570f45ee37dbbcfd9b4a7d43c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks (2021, methodology): “The work described in this paper utilizes a variant of the RawNet2 model introduced in [12] for the task of speaker veriﬁcation and applied subsequently for anti-spooﬁng [11, 13].”
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild (2022, methodology): “Originating from [39] and based on RawNet [40] and graph attention networks, AASIST [41] is representative of progress in the use of E2E architectures.”
Does Audio Deepfake Detection Generalize? (2022, methodology): “In our evaluation of ﬁxed-length input, we chose a length of four seconds, following [23].”
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection (2021, unknown): “The forth system [23] (baseline B4) uses a RawNet2 arDays 0 5 10 15 20 25 30 35 40 45 50 #s ub m is si on s”
HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis (2022, unknown): “To mitigate these issues, fake audio detection is studied (Singhal et al., 2019; Tak et al., 2021).”