CAK: Emergent Audio Effects from Minimal Deep Learning
This work enables new approaches to audio effect design for musicians and audio engineers, though it is incremental in its application of adversarial training to a specific domain.
The paper tackled the problem of generating audio effects from minimal data by training a single 3x3 convolutional kernel on 200 personalized samples, achieving emergent musical transformations through frequency-dependent temporal shifts.
We demonstrate that a single 3x3 convolutional kernel can produce emergent audio effects when trained on 200 samples from a personalized corpus. We achieve this through two key techniques: (1) Conditioning Aware Kernels (CAK), where output = input + (learned_pattern x control), with a soft-gate mechanism supporting identity preservation at zero control; and (2) AuGAN (Audit GAN), which reframes adversarial training from "is this real?" to "did you apply the requested value?" Rather than learning to generate or detect forgeries, our networks cooperate to verify control application, discovering unique transformations. The learned kernel exhibits a diagonal structure creating frequency-dependent temporal shifts that are capable of producing musical effects based on input characteristics. Our results show the potential of adversarial training to discover audio transformations from minimal data, enabling new approaches to effect design.