Light and sound pollution from our 24-hour urban lifestyle affects birds, who are singing earlier, louder, for longer, or at a higher pitch to communicate. But only those species that adapt survive. Machine Auguries questions how the city might sound with changing, homogenising, or diminishing bird populations. Aurelia worked with Daisy Ginsberg to conceive and sound design a multi-speaker installation which condenses a dawn chorus from 90 mins to 10 mins. During the piece a natural dawn chorus is taken over by artificial birds, their calls generated using machine learning. Solo recordings of chiffchaffs, great tits, redstarts, robins, thrushes, and entire dawn choruses were used to train two neural networks, pitted against each other to sing (a Generative Adversarial Network, or GAN). Reflecting on how birds develop their song from each other, a call and response of real and artificial birds spatialise the evolution of a new language. Samples taken from each stage in the GAN’s training revealing the artificial birds’ growing lifelikeness.
Sound Designer’s Scoop
“Aside from an amazing creative concept for the piece, working with nature recording legend Chris Watson was both an honour and a lot of fun. Chris provided us with some incredible recordings of British birds which we used in the mix alongside their strange, machine generated companions. We love designing bespoke loudspeaker installations and putting one in” (Chris Timpson).