‘AI musician’ composes own songs in different genres
Geneva: Scientists have developed a deep- learning computer algorithm that can generate new tunes in various musical genres and imitate a given style of music.
The “deep artificial composer” or DAC could one day generate convincing music for multiple instruments in real time, with applications ranging from video games to helping composers in the creative process, researchers said.
Developed by researchers at Ecole polytechnique federale de Lausanne (EPFL) in Switzerland, DAC generates brand-new melodies that imitate traditional folk music of Irish origin.
The generated music is not limited to Irish traditional folk music: any style of music could be used, researchers said.
It does so without plagiarising already existing ones, since melodies it writes are as original as those produced by a human composer, they said.
The DAC actually produces musical scores of melodies, symbolic music written using notation, and does not generate audio files.
“The deep artificial composer can produce complete melodies, with a beginning and an end, that are completely novel and that share features that we relate to style,” said EPFL scientists Florian Colombo.
“To my knowledge, this is the first time that an artificial neural network model has produced entire and convincing melodies. We also provide a new tool to evaluate the originality of a piece,” said Colombo, who developed the algorithm under the guidance of Wulfram Gerstner, director of the Computational Neuroscience Laboratory at EPFL. AI is already capable of composing symbolic music and is often based on implementing music theory, researchers said. What is new with the DAC is that the AI learns to compose complete melodies without any music theory from start to finish, solely based on a large database of existing music. No human post production is necessary.
EPFL’s deep artificial composer avoids traditional music theory altogether. Each style of music has its own set of rules, and existing AI generated music often uses the Western musical language of harmony and counterpoint.
The algorithm determines its own composition rules by extracting probability distributions from existing melodies using neural networks, requiring only the computation power of graphic cards that can speed up calculations by a factor of ten compared to standard computers.
The DAC extracts the style of the music by learning how a given piece of music transitions from one note to the next, and calculates the probability of the next note’s pitch and duration.