dCoNNear: An Artifact-Free Neural Network Architecture for Closed-loop Audio Signal Processing

TL;DR

dCoNNear is a novel neural network architecture designed to eliminate artifacts in closed-loop audio processing, enhancing sound quality in hearing aids and speech enhancement without introducing new distortions.

Contribution

It introduces a new DNN architecture that prevents artifact generation in closed-loop audio systems, enabling high-fidelity, artifact-free sound processing.

Findings

dCoNNear effectively prevents tonal and aliasing artifacts.

It improves perceptual sound quality in hearing aids and speech enhancement.

The architecture accurately models biophysical auditory processing stages.

Abstract

Recent advances in deep neural networks (DNNs) have significantly improved various audio processing applications, including speech enhancement, synthesis, and hearing-aid algorithms. DNN-based closed-loop systems have gained popularity in these applications due to their robust performance and ability to adapt to diverse conditions. Despite their effectiveness, current DNN-based closed-loop systems often suffer from sound quality degradation caused by artifacts introduced by suboptimal sampling methods. To address this challenge, we introduce dCoNNear, a novel DNN architecture designed for seamless integration into closed-loop frameworks. This architecture specifically aims to prevent the generation of spurious artifacts-most notably tonal and aliasing artifacts arising from non-ideal sampling layers. We demonstrate the effectiveness of dCoNNear through a proof-of-principle example within a closed-loop framework that employs biophysically realistic models of auditory processing for both normal and hearing-impaired profiles to design personalized hearing-aid algorithms. We further validate the broader applicability and artifact-free performance of dCoNNear through speech-enhancement experiments, confirming its ability to improve perceptual sound quality without introducing architecture-induced artifacts. Our results show that dCoNNear not only accurately simulates all processing stages of existing non-DNN biophysical models but also significantly improves sound quality by eliminating audible artifacts in both hearing-aid and speech-enhancement applications. This study offers a robust, perceptually transparent closed-loop processing framework for high-fidelity audio applications.