World Premiere of new music using PRiSM SampleRNN
Ireland: A Dataset | World Premiere by PRiSM Artist in residence Jennifer Walshe
26 September 2020
PRISM SampleRNN is a computer-assisted compositional tool, released in June 2020, as part of Future Music #2. It represents PRiSM’s first major contribution to the field of Machine Learning.
This Saturday saw the premiere of a new work, Ireland: A Dataset, by PRiSM Artist in Residence Jennifer Walshe. This is the first new work to incorporate material generated using PRiSM SampleRNN. Walshe asked PRISM to use Irish traditional sean-nós singing to train a model which would produce AI-generated material. This was then learned by ear by the experimental vocal group Tonnta (Robbie Blake, Elizabeth Hilliard, Bláthnaid Conroy Murphy and Simon MacHale) for the performance, which also included AI interpretations of Enya, Riverdance and the Dubliners.
The results are at once nonsensical and oddly charming: Walshe seems to be suggesting that randomization can restore mystery to traditional material.
Jennifer Walshe’s Sublime Chaos, Alex Ross, The New Yorker, October 19, 2020
Read more about the work in Walshe’s interview for The Journal of Music here.
PRiSM Lecturer in Composition, Dr Sam Salem, describes his personal journey with SampleRNN and audio synthesis, which initiated the software development, in the article A Psychogeography of Latent Space. The concepts underlying this project were introduced by PRiSM Research Software Engineer Dr Christopher Melen in the PRiSM blog article A Short History of Neural Synthesis.