SAME: A Semantically-Aligned Music Autoencoder
Researchers have developed SAME, a new autoencoder for stereo music and general audio that achieves a high temporal compression ratio while preserving reconstruction quality. This model combines a transformer backbone with semantic regularization, phase-aware losses, and improved discriminator designs. SAME offers significant computational cost benefits and is released in open-weights with two variants: SAME-L and a CPU-deployable SAME-S. AI
IMPACT New open-weight audio autoencoder could reduce computational costs for generative audio tasks.