ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection

By Massimiliano Todisco, Xin Eric Wang, Ville Vestman, Md. Sahidullah, Héctor Delgado, Andreas Nautsch, Junichi Yamagishi, N. Evans, Tomi H. Kinnunen, Kong Aik LEE. Interspeech, 2019

822 citations recorded by the source corpus.

ASVspoof, now in its third edition, is a series of community-led challenges which promote the development of countermeasures to protect automatic speaker verification (ASV) from the threat of spoofing. Advances in the 2019 edition include: (i) a consideration of both logical access (LA) and physical access (PA) scenarios and the three major forms of spoofing attack, namely synthetic, converted and replayed speech; (ii) spoofing attacks generated with state-of-the-art neural acoustic and waveform models; (iii) an improved, controlled simulation of replay attacks; (iv) use of the tandem detection cost function (t-DCF) that reflects the impact of both spoofing and countermeasures upon ASV reliability. Even if ASV remains the core focus, in retaining the equal error rate (EER) as a secondary metric, ASYspoof also embraces the growing importance of fake audio detection. ASVspoof 2019 attracted the participation of 63 research teams, with more than half of these reporting systems that improve upon the performance of two baseline spoofing countermeasures. This paper describes the 2019 database, protocols and challenge results. It also outlines major findings which demonstrate the real progress made in protecting against the threat of spoofing and fake audio.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/396af8a1241d5689a2d730cc76e947f78fe998dd

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

Translatotron 2: Robust direct speech-to-speech translation (2021, methodology): “Todisco et al. (2019); Wang et al. (2020b) showed that it was challenging to detect spoof audios generated from Jia et al. (2018), which uses the same speaker encoder-based approach as in the original Translatotron.”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, background): “53% § ASVspoof 2019 challenge [217] Wu et al.”
One-Class Learning Towards Synthetic Voice Spoofing Detection (2020, methodology): “A17 is the most difficult attack in the evaluation set [3], but our proposed system shows a significant improvement.”
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection (2021, methodology): “The LA task builds upon the ASVspoof 2015 [3] and ASVspoof 2019 LA tasks [5].”
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (2019, result): “The ASVspoof 2019 challenge, accompanied by a new dataset, brings a number of advances compared with previous editions [7, 8].”
Does Audio Deepfake Detection Generalize? (2022, neutral): “There is a significant body of work on audio spoof detection, driven largely by the ASVspoof challenges and datasets [5, 6].”
AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks (2021, methodology): “All experiments were performed using the ASVspoof 2019 logical access (LA) dataset [3, 39].”
End-to-End anti-spoofing with RawNet2 (2020, result): “For consistency with results reported in [25], t-DCF results derived according to the original min t-DCF metric in [23, 24].”
Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation (2022, positive): “We used the training and development partitions of the ASVspoof 2019 LA database [61, 62] for training and validation.”