REVIEW 4 cited by
End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Artefacts that serve to distinguish bona fide speech from spoofed or deepfake speech are known to reside in specific subbands and temporal segments. Various approaches can be used to capture and model such artefacts, however, none works well across a spectrum of diverse spoofing attacks. Reliable detection then often depends upon the fusion of multiple detection systems, each tuned to detect different forms of attack. In this paper we show that better performance can be achieved when the fusion is performed within the model itself and when the representation is learned automatically from raw waveform inputs. The principal contribution is a spectro-temporal graph attention network (GAT) which learns the relationship between cues spanning different sub-bands and temporal intervals. Using a model-level graph fusion of spectral (S) and temporal (T) sub-graphs and a graph pooling strategy to improve discrimination, the proposed RawGAT-ST model achieves an equal error rate of 1.06 % for the ASVspoof 2019 logical access database. This is one of the best results reported to date and is reproducible using an open source implementation.
Forward citations
Cited by 4 Pith papers
-
Probing Speaker Identity Sensitivity in Audio Deepfake Detectors
A new Identity Sensitivity Score flags misclassified audio deepfake detections with AUC up to 0.954, but its claim to isolate speaker-identity behavior from plain confidence is not yet controlled.
-
Generalizable Audio Spoofing Detection using Non-Semantic Representations
Frozen non-semantic TRILLson embeddings with a lightweight backend beat prior spoofing detectors on out-of-domain datasets while staying competitive in-domain.
-
Teffic-Audio: Tell Fact from Fiction
A simple Conformer deepfake detector trained with multi-source balanced sampling and diverse augmentation reaches 1.454% pooled EER on Speech-DF-Arena, first among public systems.
-
Trusted Fake Audio Detection Based on Dirichlet Distribution
Applying Dirichlet-based evidential learning to three fake audio detectors yields modest EER gains and apparently better calibration on ASVspoof, but the calibration comparison is methodologically weak.
Discussion (0). Continue with ORCID to comment.