3 accepted papers
Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale benchmark for Environmental Sound Deepfake Detection (ESDD). We propose BEAT2AASIST which extends BEATs-AASIST by splitting BEATs-der…
Recent advances in text-to-audio (TTA) and audio-to-audio (ATA) generation models have enabled the creation of highly realistic environmental sounds, raising growing concerns about malicious audio manipulation in real-world scenarios. To address this emerging threat, the ESDD 2026 Challenge was intr
Prior probing-based analyses show that individual layers specialize in distinct linguistic and semantic functions. A complementary line of work observes that deeper layers enter an alignment-dominated regime, suggesting that residual updates become largely collinear with the hidden state vectors. Th…