EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Edge-Deployed Band-Split Rotary Position Encoding Transformer for Ultra-Low-Signal-to-Noise-Ratio Unmanned Aerial Vehicle Speech Enhancement

Feifan Liu, Muying Li, Luming Guo, Hao Guo, Jie Cao, Wei Zhao, Jun Wang

Drones · 22.05.2025 · 9 (6) · 386

DOI: 10.3390/drones9060386 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 22.05.2025. Verfasst von Feifan Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Addressing the significant challenge of speech enhancement in ultra-low-Signal-to-Noise-Ratio (SNR) scenarios for Unmanned Aerial Vehicle (UAV) voice communication, particularly under edge deployment constraints, this study proposes the Edge-Deployed Band-Split Rotary Position Encoding Transformer (Edge-BS-RoFormer), a novel, lightweight band-split rotary position encoding transformer. While existing deep learning methods face limitations in dynamic UAV noise suppression under such constraints, including insufficient harmonic modeling and high computational complexity, the proposed Edge-BS-RoFormer distinctively synergizes a band-split strategy for fine-grained spectral processing, a dual-dimension Rotary Position Encoding (RoPE) mechanism for superior joint time–frequency modeling, and FlashAttention to optimize computational efficiency, pivotal for its lightweight nature and robust ultra-low-SNR performance. Experiments on our self-constructed DroneNoise-LibriMix (DN-LM) dataset demonstrate Edge-BS-RoFormer’s superiority. Under a −15 dB SNR, it achieves Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) improvements of 2.2 dB over Deep Complex U-Net (DCUNet), 25.0 dB over the Dual-Path Transformer Network (DPTNet), and 2.3 dB over HTDemucs. Correspondingly, the Perceptual Evaluation of Speech Quality (PESQ) is enhanced by 0.11, 0.18, and 0.15, respectively. Crucially, its efficacy for edge deployment is substantiated by a minimal model storage of 8.534 MB, 11.617 GFLOPs (an 89.6% reduction vs. DCUNet), a runtime memory footprint of under 500MB, a Real-Time Factor (RTF) of 0.325 (latency: 330.830 ms), and a power consumption of 6.536 W on an NVIDIA Jetson AGX Xavier, fulfilling real-time processing demands. This study delivers a validated lightweight solution, exemplified by its minimal computational overhead and real-time edge inference capability, for effective speech enhancement in complex UAV acoustic scenarios, including dynamic noise conditions. Furthermore, the open-sourced dataset and model contribute to advancing research and establishing standardized evaluation frameworks in this domain.

Zitieren

APA

Liu, F., Li, M., Guo, L., Guo, H., Cao, J., Zhao, W., & Wang, J. (2025). Edge-Deployed Band-Split Rotary Position Encoding Transformer for Ultra-Low-Signal-to-Noise-Ratio Unmanned Aerial Vehicle Speech Enhancement. Drones, 9(6), 386. https://doi.org/10.3390/drones9060386

Vancouver

Liu F, Li M, Guo L, Guo H, Cao J, Zhao W, et al. Edge-Deployed Band-Split Rotary Position Encoding Transformer for Ultra-Low-Signal-to-Noise-Ratio Unmanned Aerial Vehicle Speech Enhancement. Drones. 2025;9(6):386. doi:10.3390/drones9060386

BibTeX
@article{Liu2025,
  author = {Liu, Feifan and Li, Muying and Guo, Luming and Guo, Hao and Cao, Jie and Zhao, Wei and Wang, Jun},
  title = {Edge-Deployed Band-Split Rotary Position Encoding Transformer for Ultra-Low-Signal-to-Noise-Ratio Unmanned Aerial Vehicle Speech Enhancement},
  journal = {Drones},
  year = {2025},
  volume = {9},
  number = {6},
  pages = {386},
  doi = {10.3390/drones9060386}
}
Kostenlos starten →