XSQ-AST: An Explainable Audio Spectrogram Transformer Framework for Localising Synthetic Speech Artifacts

Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, provided through dedicated techniques such as AudioSeal, or deployed by commercial platforms such as ElevenLabs. We identify a previously uncharacterized liability: when synthetic speech is watermarked and human speech is not, detectors trained alongside latch onto the watermark as a spurious "watermark => fake" shortcut. This single feature yields three coupled failures: generalization degradation (model performance deteriorates on unseen data), strip-to-evade (a watermarked fake escapes once unwatermarked), and mark-to-frame (watermarking a real voice flags it as fake). In a controlled white-box experiment, a watermark-trained detector shows all three (for example, mark-to-frame lifts Equal Error Rate from 16% to 75%). In a black-box test of a commercial API, we show that adding a watermark to real speech disguises it as fake. However, this shortcut is fixable: retraining with the watermark on both classes decorrelates it and restores clean behavior. We release experiment data as a paired clean-versus-watermarked corpus (WASP).

Attributing a synthetic utterance to its originating system remains an open challenge: closed-set models fail to reject unseen synthesizers and produce overconfident predictions. To address this, we propose a dual-branch gated fusion framework that pairs XLSR-53 with CORES, a 66-dimensional descriptor that, unlike prior Linear Filter Bank (LFB)-only work, spans cepstral, oscillatory, rhythmic, energy, and spectral dimensions to capture complementary synthesis artifacts. Our analysis shows XLSR-53 remains discriminative in-domain (ID) while CORES generalizes stably under distribution shift (OOD), yet their naive concatenation fails due to SSL representational imbalance. To resolve this, an input-conditioned gate adaptively weights each branch under joint training with cross-entropy, an energy margin loss for ID/OOD separation, and a gate diversity term. On the MLAAD benchmark, our system achieves 97.6% ID accuracy, 4.9% EERc, and an 83.5% relative FPR95 reduction over the Interspeech 2025 baseline.

As the accuracy of speech deepfake detection improves with the use of self-supervised representations such as wav2vec 2.0 and HuBERT, understanding why the speech is classified as bona fide or deepfake remains an open challenge. In pursuit of more trustworthy and interpretable artificial intelligence, we introduce a phoneme-level analysis framework that connects model predictions to measurable phonetic units. Our post-hoc explainability method is generally applicable to a variety of speech deepfake detection systems based on convolutional neural networks since it leverages Gradient-weighted Class Activation Mapping in conjunction with speech recognition to generate saliency maps aligned with phonemes and pauses. This pipeline reveals statistically significant attack- and speaker-dependent phonetic cues associated with spoofed speech in terms that humans can understand. Experiments using ASVspoof 5 show comparable detection performance to similar architectures while providing linguistic interpretations across speakers and spoofing conditions.