Differential Music: Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals
This addresses the problem of generating coherent music for applications in creative AI, though it is incremental with a novel encoding approach.
The paper tackled automated music composition by developing an LSTM-based generative model that encodes music using melodic and harmonic intervals instead of absolute pitch, resulting in compositions that sound musical and tonal but with excessive modulations.
This paper presents a generative AI model for automated music composition with LSTM networks that takes a novel approach at encoding musical information which is based on movement in music rather than absolute pitch. Melodies are encoded as a series of intervals rather than a series of pitches, and chords are encoded as the set of intervals that each chord note makes with the melody at each timestep. Experimental results show promise as they sound musical and tonal. There are also weaknesses to this method, mainly excessive modulations in the compositions, but that is expected from the nature of the encoding. This issue is discussed later in the paper and is a potential topic for future work.