Model Assignments

EARLY MODELS, NON-MAGENTA MODELS:

Assigned: Hafi
Feynman Liang, BachBot:
http://bachbot.com

Assigned: Max
FolkRNN:
https://folkrnn.org/, https://github.com/IraKorshunova/folk-rnn

Assigned: Luming
Wavenet (DeepMind version):
https://deepmind.com/blog/wavenet-generative-model-raw-audio/

Assigned: Ayal
SampleRNN:
https://github.com/soroushmehr/sampleRNN_ICLR2017

MAGENTA MODELS:

https://github.com/tensorflow/magenta/tree/master/magenta/models

Assigned: Sukanya
Drums RNN:
Applies language modeling to drum track generation using an LSTM.

Assigned: Sofia
Image Stylization:
A "Multistyle Pastiche Generator" that generates artistics representations of photographs. non-music

Assigned: Xiran
Improv RNN:
Generates melodies a la Melody RNN, but conditions the melodies on an underlying chord progression.

Assigned: Youjin
Melody RNN:
Applies language modeling to melody generation using an LSTM. Blog Post

Assigned: Jiwon
Music VAE:
A hierarchical recurrent variational autoencoder for music.

Assigned: Joohyun
NSynth:
"Neural Audio Synthesis" as described in NSynth: Neural Audio Synthesis with WaveNet Autoencoders.

Assigned: Phil
Onsets and Frames:
Automatic piano music transcription model as described in Onsets and Frames: Dual-Objective Piano Transcription

Assigned: Itay
Performance RNN:
Applies language modeling to polyphonic music using a combination of note on/off, timeshift, and velocity change events.

Assigned: Xinyi
Pianoroll RNN-NADE:
Applies language modeling to polyphonic music generation using an LSTM combined with a NADE, an architecture called an RNN-NADE. Based on the architecture described in Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription.

Assigned: Guillermo
Polyphony RNN:
Applies language modeling to polyphonic music generation using an LSTM. Based on the BachBot architecture described in Automatic Stylistic Composition of Bach Choralies with Deep LSTM.

***** Assigned to Nicolas**** RL Tuner:
Takes an LSTM that has been trained to predict the next note in a monophonic melody and enhances it using reinforcement learning (RL).

Assigned: MH
Sketch RNN:
A recurrent neural network model for generating sketches. non-music