Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exiting

TL;DR

This paper introduces Dynamic nsNet2, an early-exiting deep noise suppression model that balances accuracy and resource efficiency by allowing computation to halt at various stages, suitable for resource-constrained devices.

Contribution

It proposes a novel adaptive architecture that dynamically adjusts computation depth, improving efficiency without significantly sacrificing noise suppression performance.

Findings

Effective trade-offs between accuracy and computational complexity demonstrated.

Model achieves resource savings by early exiting at different stages.

Adapted architecture accounts for dynamic information flow.

Abstract

Although deep learning has made strides in the field of deep noise suppression, leveraging deep architectures on resource-constrained devices still proved challenging. Therefore, we present an early-exiting model based on nsNet2 that provides several levels of accuracy and resource savings by halting computations at different stages. Moreover, we adapt the original architecture by splitting the information flow to take into account the injected dynamism. We show the trade-offs between performance and computational complexity based on established metrics.