GGA-MG: Generative Genetic Algorithm for Music Generation
This addresses music generation for AI applications, but it is incremental as it builds on existing genetic algorithms and LSTM methods.
The paper tackles the problem of automatic melody generation by proposing a Generative Genetic Algorithm (GGA) that uses an LSTM as an objective function, trained on a spectrum of melodies from bad to good, and results show it generates eligible melodies with natural transitions and no rhythm errors.
Music Generation (MG) is an interesting research topic that links the art of music and Artificial Intelligence (AI). The goal is to train an artificial composer to generate infinite, fresh, and pleasurable musical pieces. Music has different parts such as melody, harmony, and rhythm. In this paper, we propose a Generative Genetic Algorithm (GGA) to produce a melody automatically. The main GGA uses a Long Short-Term Memory (LSTM) recurrent neural network as the objective function, which should be trained by a spectrum of bad-to-good melodies. These melodies have to be provided by another GGA with a different objective function. Good melodies have been provided by CAMPINs collection. We have considered the rhythm in this work, too. The experimental results clearly show that the proposed GGA method is able to generate eligible melodies with natural transitions and without rhythm error.