LAV: Audio-Driven Dynamic Visual Generation with Neural Compression and StyleGAN2

TL;DR

LAV is a novel system that uses neural audio compression embeddings as latent inputs to StyleGAN2, enabling semantically coherent, audio-driven visual generation.

Contribution

It introduces a new method combining neural audio compression with StyleGAN2, using embeddings as latent representations for dynamic visual synthesis.

Findings

EnCodec embeddings effectively drive StyleGAN2 for visual generation.

The approach preserves semantic richness in audio-visual translation.

LAV demonstrates potential for artistic and computational applications.

Abstract

This paper introduces LAV (Latent Audio-Visual), a system that integrates EnCodec's neural audio compression with StyleGAN2's generative capabilities to produce visually dynamic outputs driven by pre-recorded audio. Unlike previous works that rely on explicit feature mappings, LAV uses EnCodec embeddings as latent representations, directly transformed into StyleGAN2's style latent space via randomly initialized linear mapping. This approach preserves semantic richness in the transformation, enabling nuanced and semantically coherent audio-visual translations. The framework demonstrates the potential of using pretrained audio compression models for artistic and computational applications.