# LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search

arXiv: https://arxiv.org/abs/2404.14063 · HTML: https://mlsanity.com/paper/2404.14063/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 6 of 6)

- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [RAVE: A variational autoencoder for fast and high-quality neural audio synthesis](https://mlsanity.com/paper/2111.05011/) (2021)
- [VampNet: Music Generation via Masked Acoustic Token Modeling](https://mlsanity.com/paper/2307.04686/) (2023)
- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution](https://mlsanity.com/paper/2104.06106/) (2021)

## Abstract (arXiv)

Evolutionary Algorithms and Generative Deep Learning have been two of the most powerful tools for sound generation tasks. However, they have limitations: Evolutionary Algorithms require complicated designs, posing challenges in control and achieving realistic sound generation. Generative Deep Learning models often copy from the dataset and lack creativity. In this paper, we propose LVNS-RAVE, a method to combine Evolutionary Algorithms and Generative Deep Learning to produce realistic and novel sounds. We use the RAVE model as the sound generator and the VGGish model as a novelty evaluator in the Latent Vector Novelty Search (LVNS) algorithm. The reported experiments show that the method can successfully generate diversified, novel audio samples under different mutation setups using different pre-trained RAVE models. The characteristics of the generation process can be easily controlled with the mutation parameters. The proposed algorithm can be a creative tool for sound artists and musicians.