Monaural speech enhancement on drone via Adapter based transfer learning

TL;DR

This paper introduces a transfer learning approach using a frequency domain adapter to improve monaural speech enhancement on drones, effectively handling ego-noise with less computational cost.

Contribution

It proposes a novel frequency domain bottleneck adapter for transfer learning, enabling efficient speech enhancement on drones without extensive fine-tuning.

Findings

Effective speech quality enhancement demonstrated

More computationally efficient than traditional fine-tuning

Robust across different drone noise scenarios

Abstract

Monaural Speech enhancement on drones is challenging because the ego-noise from the rotating motors and propellers leads to extremely low signal-to-noise ratios at onboard microphones. Although recent masking-based deep neural network methods excel in monaural speech enhancement, they struggle in the challenging drone noise scenario. Furthermore, existing drone noise datasets are limited, causing models to overfit. Considering the harmonic nature of drone noise, this paper proposes a frequency domain bottleneck adapter to enable transfer learning. Specifically, the adapter's parameters are trained on drone noise while retaining the parameters of the pre-trained Frequency Recurrent Convolutional Recurrent Network (FRCRN) fixed. Evaluation results demonstrate the proposed method can effectively enhance speech quality. Moreover, it is a more efficient alternative to fine-tuning models for various drone types, which typically requires substantial computational resources.