MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer

09/20/2018
by   Gino Brunner, et al.
0

We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by automatically changing pitches, dynamics and instruments of a music piece from, e.g., a Classical to a Jazz style. We evaluate the efficacy of the style transfer by training separate style validation classifiers. Our model can also interpolate between short pieces of music, produce medleys and create mixtures of entire songs. The interpolations smoothly change pitches, dynamics and instrumentation to create a harmonic bridge between two music pieces. To the best of our knowledge, this work represents the first successful attempt at applying neural style transfer to complete musical compositions.

READ FULL TEXT
research
05/10/2021

MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with One Transformer VAE

Transformers and variational autoencoders (VAE) have been extensively em...
research
02/10/2021

Self-Supervised VQ-VAE For One-Shot Music Style Transfer

Neural style transfer, allowing to apply the artistic style of one image...
research
09/20/2018

Symbolic Music Genre Transfer with CycleGAN

Deep generative models such as Variational Autoencoders (VAEs) and Gener...
research
05/30/2019

Musical Composition Style Transfer via Disentangled Timbre Representations

Music creation involves not only composing the different parts (e.g., me...
research
09/29/2019

MG-VAE: Deep Chinese Folk Songs Generation with Specific Regional Style

Regional style in Chinese folk songs is a rich treasure that can be used...
research
10/12/2021

Music Sentiment Transfer

Music sentiment transfer is a completely novel task. Sentiment transfer ...
research
10/25/2021

Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience

The subjective evaluation of music generation techniques has been mostly...

Please sign up or login with your details

Forgot password? Click here to reset