SnakeSynth: New Interactions for Generative Audio Synthesis

I present "SnakeSynth," a web-based lightweight audio synthesizer that combines audio generated by a deep generative model and real-time continuous two-dimensional (2D) input to create and control variable-length generative sounds through 2D interaction gestures. Interaction gestures are touch and mobile-compatible and made with analogies to strummed, bowed, brushed, and plucked musical instrument controls. Point-and-click and drag-and-drop gestures directly control audio playback length and intensity. I show that I can modulate sound length and intensity by interacting with a programmable 2D grid and leveraging the speed and ubiquity of web browser-based audio and hardware acceleration to generate time-varying high-fidelity sounds with real-time interactivity. SnakeSynth adaptively reproduces and interpolates between sounds encountered during model training, notably without long training times, and I briefly discuss possible futures for deep generative models as an interactive paradigm for musical expression.