Melody Generation using an Interactive Evolutionary Algorithm
This work addresses the challenge of music quality evaluation in AI-generated music, offering an incremental improvement for researchers and practitioners in computational creativity.
The paper tackles the problem of evaluating machine-generated music by developing an interactive evolutionary algorithm that uses human expertise for scoring during training, modeled with a Bi-LSTM network, resulting in the generation of pleasurable melodies with desired styles and pieces, and it is reported to be quite fast compared to state-of-the-art data-oriented evolutionary systems.
Music generation with the aid of computers has been recently grabbed the attention of many scientists in the area of artificial intelligence. Deep learning techniques have evolved sequence production methods for this purpose. Yet, a challenging problem is how to evaluate generated music by a machine. In this paper, a methodology has been developed based upon an interactive evolutionary optimization method, with which the scoring of the generated melodies is primarily performed by human expertise, during the training. This music quality scoring is modeled using a Bi-LSTM recurrent neural network. Moreover, the innovative generated melody through a Genetic algorithm will then be evaluated using this Bi-LSTM network. The results of this mechanism clearly show that the proposed method is able to create pleasurable melodies with desired styles and pieces. This method is also quite fast, compared to the state-of-the-art data-oriented evolutionary systems.