Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label

TL;DR

This paper presents a CVAE-based method for intuitive, real-time timbre control in wavetable synthesis using semantic labels like bright or warm, simplifying complex parameter adjustments for users.

Contribution

It introduces a novel semantic label-based timbre control approach in wavetable synthesis utilizing a CVAE model for real-time, intuitive manipulation.

Findings

Effective real-time timbre control demonstrated

Semantic labels enable intuitive sound customization

Model captures wavetable nuances accurately

Abstract

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.