Music Production

This is a project on music generation / Production. In a nutshell, we aim to generate polyphonic music of multiple tracks (instruments). The proposed models are able to generate music either from scratch, or by accompanying a track given by the user.

We train the model with training data collected from Lakh Pianoroll Dataset to generate pop song phrases consisting of bass, drums, guitar, piano and strings tracks.

Install dependencies

Using pip

# Install the dependencies
pip install -r requirements.txt

Prepare training data

The training data is collected from Lakh Pianoroll Dataset (LPD), a new multitrack pianoroll dataset¡.

# Download the training data
./scripts/download_data.sh

# Store the training data to shared memory
./scripts/process_data.sh

Scripts

I have written Several shell scripts for easy managing the experiments. (See here for scripts detailed documentation.)

Note : execute these scripts from the root directory of the project.

Command to set up a new experiment with default settings.

# Set up a new experiment
./scripts/setup_exp.sh "./exp/my_experiment/" "Some notes on my experiment"

You can modify the configuration and model parameter files for experimental settings.

You can either train the model:

# Train the model
./scripts/run_train.sh "./exp/my_experiment/" "0"

OR .. run the experiment (training + inference + interpolation):

# Run the experiment
./scripts/run_exp.sh "./exp/my_experiment/" "0"

OR .. after training you can do inference AND interpolatioln separately.

=> Perform inference from a trained model:

# Run inference from a pretrained model
./scripts/run_inference.sh "./exp/default/" "0"

=> Perform interpolation from a trained model:

# Run interpolation from a pretrained model
./scripts/run_interpolation.sh "./exp/default/" "0"

Papers

Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
Hao-Wen Dong and Yi-Hsuan Yang
Retrieval Conference_ (ISMIR), 2018.

paper]

MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
Hao-Wen Dong, Wen-Yi Hsiao, Li-Chia Yang and Yi-Hsuan Yang,

[paper]

[code]

MuseGAN: Demonstration of a Convolutional GAN Based Model for Generating Multi-track Piano-rolls
Hao-Wen Dong, Wen-Yi Hsiao, Li-Chia Yang and Yi-Hsuan Yang