Conditioning Deep Generative Raw Audio Models for Structured Automatic Music
This addresses the challenge of creating structured automatic music with audio fidelity for applications in music production, though it is incremental by integrating existing methods.
The paper tackles the problem of generating realistic-sounding yet structured music by combining symbolic and raw audio models, using an LSTM for melodic structure and WaveNet for audio generation, resulting in novel compositions.
Existing automatic music generation approaches that feature deep learning can be broadly classified into two types: raw audio models and symbolic models. Symbolic models, which train and generate at the note level, are currently the more prevalent approach; these models can capture long-range dependencies of melodic structure, but fail to grasp the nuances and richness of raw audio generations. Raw audio models, such as DeepMind's WaveNet, train directly on sampled audio waveforms, allowing them to produce realistic-sounding, albeit unstructured music. In this paper, we propose an automatic music generation methodology combining both of these approaches to create structured, realistic-sounding compositions. We consider a Long Short Term Memory network to learn the melodic structure of different styles of music, and then use the unique symbolic generations from this model as a conditioning input to a WaveNet-based raw audio generator, creating a model for automatic, novel music. We then evaluate this approach by showcasing results of this work.