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.
(See document for exact affiliation information.)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
