Omid Alemi - PhD Thesis

Supplementary Material

Chapter 8: GrooveNet 2.0

Generated Movements - Model Trained on Analytical Features

Songs From the Training Data

Songs Outside of the Training Data

Generated Movements - Model Trained on WaveNet Embeddings

Songs From the Training Data

Songs Outside of the Training Data

Real-Time Generation

Note: The model used in the real-time demo is different from the above models. It is trained on analytical audio features, but based on the data from a different performer. In the demo video, the first three songs are not in the training set.

Demo of GrooveNet Real-Time Engine (local copy)