Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label
This addresses the need for more accessible timbre control in music production for users without technical expertise, though it appears incremental as it applies an existing CVAE method to a specific domain.
This research tackled the problem of complex timbre control in wavetable synthesis by introducing a method using a conditional variational autoencoder (CVAE) with semantic labels like bright and warm, enabling real-time and intuitive timbre control.
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.