mlsanityData to 14 Oct 2026

Architecture and Affordances of PLAUD: Performative Latents and Unsupervised DDSP

arXiv 2608.13724 ↗First posted 13 Aug 2026cs.SD cs.HC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

18 of 34 references.

References · 18

  1. 2019An Introduction to Variational Autoencoderscited by 1,000
  2. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  3. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  4. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  5. 2018Understanding disentangling in β-VAEcited by 335
  6. 2020DDSP: Differentiable Digital Signal Processingcited by 178
  7. 2021RAVE: A variational autoencoder for fast and high-quality neural audio synthesiscited by 73
  8. 2021MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modelingcited by 32
  9. 2024Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitationscited by 24
  10. 2023A Review of Differentiable Digital Signal Processing for Music & Speech Synthesiscited by 20
  11. 2020I'm Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitchcited by 17
  12. 2022Sinusoidal Frequency Estimation by Gradient Descentcited by 15
6 more
  1. 2021Machine Learning Uncertainty as a Design Material: A Post-Phenomenological Inquirycited by 14
  2. 2021Active Divergence with Generative Deep Learning -- A Survey and Taxonomycited by 12
  3. 2023NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbankscited by 4
  4. 2023Sound Design Strategies for Latent Audio Space Explorations Using Deep Learning Architecturescited by 1
  5. 2025Neutone SDK: An Open Source Framework for Neural Audio Processingcited by 1
  6. 2025Exploring Situated Stabilities of a Rhythm Generation System through Variational Cross-Examinationcited by 1

Built on by

Not cited yet.