UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021
arXiv:2107.12018 · doi:10.21437/ASVSPOOF.2021-12
Abstract
In this paper, we present UR-AIR system submission to the logical access (LA) and the speech deepfake (DF) tracks of the ASVspoof 2021 Challenge. The LA and DF tasks focus on synthetic speech detection (SSD), i.e. detecting text-to-speech and voice conversion as spoofing attacks. Different from previous ASVspoof challenges, the LA task this year presents codec and transmission channel variability, while the new task DF presents general audio compression. Built upon our previous research work on improving the robustness of the SSD systems to channel effects, we propose a channel-robust synthetic speech detection system for the challenge. To mitigate the channel variability issue, we use an acoustic simulator to apply transmission codec, compression codec, and convolutional impulse responses to augmenting the original datasets. For the neural network backbone, we propose to use Emphasized Channel Attention, Propagation and Aggregation Time Delay Neural Networks (ECAPA-TDNN) as our primary model. We also incorporate one-class learning with channel-robust training strategies to further learn a channel-invariant speech representation. Our submission achieved EER 20.33% in the DF task; EER 5.46% and min-tDCF 0.3094 in the LA task.
To appear in Proc. ASVspoof 2021 Workshop
References in corpus (7)
- ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
- The BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF
- Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals
- Human Perception of Audio Deepfakes
- VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
- An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems
- Replay and Synthetic Speech Detection with Res2net Architecture
Cited by in corpus (6)
- A Survey on Speech Deepfake Detection
- GMM-ResNet2: Ensemble of Group ResNet Networks for Synthetic Speech Detection
- Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
- Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion
- Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
- Phase perturbation improves channel robustness for speech spoofing countermeasures