Real-time Timbre Remapping with Differentiable DSP
This addresses the limitation of flattening timbral expression in music synthesis, particularly for snare drum performances, though it is incremental as it builds on existing differentiable DSP methods.
The paper tackled the problem of preserving timbral expression in audio-driven synthesis by mapping timbral differences from an input signal to synthesizer controls, using a differentiable DSP approach with a feature difference loss. They demonstrated real-time timbre remapping from acoustic snare drums to a TR-808 synthesizer model.
Timbre is a primary mode of expression in diverse musical contexts. However, prevalent audio-driven synthesis methods predominantly rely on pitch and loudness envelopes, effectively flattening timbral expression from the input. Our approach draws on the concept of timbre analogies and investigates how timbral expression from an input signal can be mapped onto controls for a synthesizer. Leveraging differentiable digital signal processing, our method facilitates direct optimization of synthesizer parameters through a novel feature difference loss. This loss function, designed to learn relative timbral differences between musical events, prioritizes the subtleties of graded timbre modulations within phrases, allowing for meaningful translations in a timbre space. Using snare drum performances as a case study, where timbral expression is central, we demonstrate real-time timbre remapping from acoustic snare drums to a differentiable synthesizer modeled after the Roland TR-808.