Robert Laidlow & PRiSM

Owen using the engine

Alter (2019) for mezzo-soprano and ensemble was written as a response to Ada Lovelace’s idea that computers might one day write music of their own, and as such utilises several generative machine learning algorithms as collaborative and interactive tools in the compositional process. In some sense, it is a field test of these algorithms and their ability to be creative catalysts: how adaptable they are to a specific project, what effect including them has on the composer and performers, how an audience versed in contemporary music might respond to them. It combines models in the symbolic-generative (MuseNet), audio-generative (WaveNet), and text-generative (WordRNN and GPT-2) domains to create a musical structure defined by the machine learning process, where the results of neural networks at different stages of training exist on a spectrum between being showcased without alteration to being radically transformed by the composer. There are also dramatic elements to the piece, including the 3D-printed percussion instrument on stage, modelled on the proto-computers of Charles Babbage that inspired Lovelace.

https://www.robertlaidlow.co.uk/alter