Architecture and Affordances of PLAUD: Performative Latents and Unsupervised DDSP

2026-08-13

AI Summary

This study addresses the lack of performativity and small-sample training challenges in live electronic music neural synthesizers by proposing PLAUD. Built upon NoiseBandNet and variational DDSP, this method innovatively introduces "bending operations," including component constraints and waveform shaping, to directly intervene in the synthesis chain. Furthermore, it integrates Transformer priors with multi-scale adversarial losses to optimize training. Experimental results demonstrate that PLAUD achieves efficient few-shot learning and enables real-time interactive control via Max for Live. Crucially, this work validates that architectural inductive biases play a decisive role in enhancing the expressive performance capabilities of neural synthesizers, thereby bridging the gap between computational synthesis and live musical interaction.

Abstract

PLAUD (Performative Latents and Unsupervised DDSP) is a neural synthesizer and Max for Live instrument for live electronic music, built on NoiseBandNet and trained on small personal sound corpora. We present its architecture, combining a variational DDSP synthesis model, latent smoothing, multi-scale spectral and adversarial losses, and an optional transformer prior, alongside a set of bending operations that intervene directly in the synthesis chain: component limiting, waveshaping, and prior feedback. The Max for Live interface exposes control generation, trajectory sampling, and modulation as primary modes of interaction. Throughout, we thread an affordance analysis arguing that the system's performative character follows from architectural decisions rather than being designed on top of them. The paper contributes both a technical account of the system and a situated affordance analysis of its role in live electronic music performance.

Problem

• Neural Synthesizer
• Live Electronic Music
• Affordance Analysis
• Performative Latents

Innovation

• Performative Latents
• Unsupervised DDSP
• Bending Operations
• Neural Synthesizer
• Affordance Analysis