Embodying the Voice with AI

This practice-as-research project was based on post-Grotowskian traditions of psychophysical actor training. Diana Serbanescu, the research lead, wanted to try to use the synthetic voice – the voice of the technology – to both enhance the embodied training and to enable embodied creative composition.

For this project we used wearable AI, designed by artist Mika Satomi. The collar came with bend sensors that could be attached to any eight points on the body. The sensor data was processed and gathered locally on a Bela board, and could be streamlined in real-time. A speaker sits on the front of the collar, emitting sounds that can react to the position of the sensors — to how the performer moves their body.

These sensor data are lists of numbers, which can be sonified or visualised in various ways, creating aural or visual cartographies of movement captured in flight. It’s a hyper-simplification of the reality of movement, yet it has something essential: it’s the beginning of a digital body-language, which the performer is able to connect to, understand and alter through her physicality.

Our early investigations were inspired by Bell Lab’s Voder, the first attempt to electronically synthesise human speech by breaking it down into its acoustic components.

The results of this research were documented by Scott de la Hunta, and are housed on Motionbank.

Ilona Krawczyk participated in the project as a workshop lead and research advisor on embodied voice