Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance

06/16/2020
by   Hao Hao Tan, et al.
0

We present a controllable neural audio synthesizer based on Gaussian Mixture Variational Autoencoders (GM-VAE), which can generate realistic piano performances in the audio domain that closely follows temporal conditions of two essential style features for piano performances: articulation and dynamics. We demonstrate how the model is able to apply fine-grained style morphing over the course of synthesizing the audio. This is based on conditions which are latent variables that can be sampled from the prior or inferred from other pieces. One of the envisioned use cases is to inspire creative and brand new interpretations for existing pieces of piano music.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset