SOURCE-LINKED INTELLIGENCE

SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

As generative audio models grow in complexity, the computational and ecological costs of synthesizing everyday sounds have become increasingly prohibitive, often requiring industrial-scale resources and massive datasets. In this paper, we present SCAPES: a Semantically Conditioned Autoregressive Prior for Environmental Sounds. SCAPES is a lightweight, resource-efficient generative model designed to synthesize high-fidelity environmental textures through high-level semantic control. By operating on the continuous latent manifold of a neural audio codec, our approach bypasses the rigid structura

Read original source ↗ Open in workspace

recordType

paper

region

Global