Knowledge-Driven Optimization of Reverberation Parameters Using Declarative Audio Constraints

Haußmann N, Everardo F. Knowledge-Driven Optimization of Reverberation Parameters Using Declarative Audio Constraints. In: Convention Paper. Audio Engineering Society; 2026. Paper 10311. Available from: https://aes.org/publications/elibrary-page/?id=23203

@inproceedings{Hausmann2026_23203,
  author = {Haußmann, Noah and Everardo, Flavio},
  title = {{Knowledge-Driven Optimization of Reverberation Parameters Using Declarative Audio Constraints}},
  note = {Paper 10311},
  year = {2026},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23203}
}

TY  - CPAPER
TI  - Knowledge-Driven Optimization of Reverberation Parameters Using Declarative Audio Constraints
AU  - Haußmann, Noah
AU  - Everardo, Flavio
M1  - Paper 10311
PY  - 2026
DA  - 2026/05/28
UR  - https://aes.org/publications/elibrary-page/?id=23203
PB  - Audio Engineering Society
LA  - en
AB  - Artificial reverberation is a fundamental process in music production and audio post-production. However, the large and highly interdependent parameter spaces of modern reverberation algorithms make the identification of perceptually optimal configurations difficult, particularly when attempting to minimize artifacts. This paper presents a knowledge-driven framework for reverberation parameter optimization that evaluates candidate configurations using rule-based audio quality constraints derived from perceptual and signal-processing principles. The system automatically detects and prevents common artifacts including spectral obfuscation, clipping, spatial collapse, and ringing phenomena. Instead of relying on data-driven training methods, the proposed approach uses declarative reasoning to represent audio engineering knowledge and methodically limit the scope of parameter exploration. Experimental evaluation demonstrates that the framework successfully reduces artifact occurrence across diverse signals while maintaining computational feasibility. The results suggest that knowledge-based reasoning can provide an interpretable and controllable alternative to data-driven optimization strategies in audio signal processing.
ER  -