# Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label

arXiv: https://arxiv.org/abs/2410.18628 · HTML: https://mlsanity.com/paper/2410.18628/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [GANSynth: Adversarial Neural Audio Synthesis](https://mlsanity.com/paper/1902.08710/) (2019)
- [RAVE: A variational autoencoder for fast and high-quality neural audio synthesis](https://mlsanity.com/paper/2111.05011/) (2021)

## Abstract (arXiv)

Synthesizers are essential in modern music production. However, their complex timbre parameters, often filled with technical terms, require expertise. This research introduces a method of timbre control in wavetable synthesis that is intuitive and sensible and utilizes semantic labels. Using a conditional variational autoencoder (CVAE), users can select a wavetable and define the timbre with labels such as bright, warm, and rich. The CVAE model, featuring convolutional and upsampling layers, effectively captures the wavetable nuances, ensuring real-time performance owing to their processing in the time domain. Experiments demonstrate that this approach allows for real-time, effective control of the timbre of the wavetable using semantic inputs and aims for intuitive timbre control through data-based semantic control.