Towards Controllable Audio Texture Morphing
This addresses the need for customizable generative audio models for sound synthesis, though it appears incremental as it builds on existing GAN and conditioning techniques.
The paper tackles the problem of controllable audio texture morphing by proposing a GAN conditioned on soft-labels from an audio classifier, achieving smooth morphing with similar or better performance than state-of-the-art methods.
In this paper, we propose a data-driven approach to train a Generative Adversarial Network (GAN) conditioned on "soft-labels" distilled from the penultimate layer of an audio classifier trained on a target set of audio texture classes. We demonstrate that interpolation between such conditions or control vectors provides smooth morphing between the generated audio textures, and shows similar or better audio texture morphing capability compared to the state-of-the-art methods. The proposed approach results in a well-organized latent space that generates novel audio outputs while remaining consistent with the semantics of the conditioning parameters. This is a step towards a general data-driven approach to designing generative audio models with customized controls capable of traversing out-of-distribution regions for novel sound synthesis.