From Spectrograms to Shallow Speech SSL: Audio-Frontend Design for Generator-Disjoint and Low-Latency Audio--Visual Deepfake Detection
Video-mediated conversational systems rely on synchronized speech and facial video, making audio--visual input integrity important for reliable perception. We study audio-frontend design in a fixed MRDF (Modality-Regularization-based DeepFake)-based pipeline with AV-HuBERT visual processing and an MSCT (multi-scale cross-modal transformer) fusion encoder. We compare spectrogram-style log-filterbank features with frozen wav2vec~2.0 and WavLM representations, dual-SSL fusion, executed depth, and shallow-layer aggregation. Across three training runs, full wav2vec~2.0 improves mean macro AUROC from $84.19\%$ to $87.19\%$ on generator-disjoint MMDF. Six-layer execution further improves detecti...
| Authors | Qiwu Wen, Jahangir Alam, Eric Charton |
|---|---|
| Primary category | cs.SD |
| Published | 16 October 2026 |
| Last updated at source | 16 October 2026 |
Popularity, last 4 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.