The secrets behind traditional folk music from across the globe and dating back thousands of years are likely to be revealed by using artificial intelligence, according to a leading academic expert. Speaking at Folk Music Analysis UK, a three-day event showcasing cutting edge technological research methods and findings using ethnomusicology and computational analysis at Birmingham City University, Dr. Islah Ali-MacLachlan highlighted advances in the field which now allow for greater understanding of the cultural data embedded in folk music. The senior lecturer in audio engineering and acoustics said, "In this era of streaming, music discovery, digitization and algorithms, one of the last bastions of music to be extensively and accurately mapped as well as understood is traditional folk music from across the globe. Sounds that have taken hundreds, if not thousands, of years to evolve, are full of human, cultural, religious, societal and geographical intricacies that we will benefit from understanding. The Folk Music Analysis workshop is a chance to discuss worldwide folk music traditions and the tools we use to extract information about them."

Lullabies have been helping people drift off to sleep since 2,000 BC - and now, more than 4,000 years latera an AI machine has made its own relaxing tune. Scientists have produced two tunes - one by Scottish composer Eddie McGuire and the other created by neural networks, in an attempt to see which one is better. The AI-created lullaby was trained using sheet music in a computer-readable format, from which it developed a sense of harmony and rhythm, and it claims to be able to help cure insomnia. The AI-created music was trained using sheet music in a computer-readable format from which it developed a sense of harmony and rhythm. It was created through deep learning, which is based on layers of artificial neural networks inspired by the brain.

The "deep artificial composer", or "DAC" for short, generates brand-new melodies that imitate traditional folk music of Irish or Klezmer origin. It does so without plagiarizing already existing ones, since melodies it writes are as original as those produced by a human composer. The results were presented in April at this year's edition of the Evostar conference. 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," says Swiss Federal Institute of Technology in Lausanne (EPFL) scientists Florian Colombo who developed the artificial intelligence under the guidance of Wulfram Gerstner, director of the Computational Neuroscience Laboratory. "To my knowledge, this is the first time that an artificial neural network model has produced entire and convincing melodies.