VaPar Synth -- A Variational Parametric Model for Audio Synthesis
This work addresses the problem of achieving more flexible control in audio synthesis for applications in music and sound design, but it appears incremental as it builds on existing variational autoencoder methods.
The paper tackled audio synthesis by proposing a variational parametric synthesizer that uses a conditional variational autoencoder on a parametric representation for flexible control over musical attributes like pitch, resulting in demonstrated capabilities for reconstructing and generating instrumental tones with pitch control.
With the advent of data-driven statistical modeling and abundant computing power, researchers are turning increasingly to deep learning for audio synthesis. These methods try to model audio signals directly in the time or frequency domain. In the interest of more flexible control over the generated sound, it could be more useful to work with a parametric representation of the signal which corresponds more directly to the musical attributes such as pitch, dynamics and timbre. We present VaPar Synth - a Variational Parametric Synthesizer which utilizes a conditional variational autoencoder (CVAE) trained on a suitable parametric representation. We demonstrate our proposed model's capabilities via the reconstruction and generation of instrumental tones with flexible control over their pitch.