Spatial-U-Net: A multi-channel speech enhancement framework for low signal-to-noise ratio scenario
The Journal of the Acoustical Society of America · 01.10.2025 · 158 (4_Supplement) · A475-A475
DOI: 10.1121/10.0041587 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, erschienen am 01.10.2025. Verfasst von Yifei Wei und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Speech enhancement for drone audition is highly challenging due to the extremely low signal-to-noise ratio (e.g. SNR < −15 dB) which is caused by the ego-noise from the rotors. Despite recent advances, most deep learning-based speech enhancement methods for drone audition only focus on single-channel inputs. Even among the few methods designed for multi-channel audio, the enhanced output is often reduced to single-channel, thereby discarding valuable spatial information which is essential for downstream processing tasks. In this paper, we propose Spatial-U-Net, a multi-channel end-to-end deep learning framework designed to suppress drone noise directly in time domain with multi-channel outputs. Based on Wave-U-Net, this model introduces attention mechanism and a hybrid loss combining mean squared error (MSE) and perceptual loss, to improve both signal recognizability and perceptual quality. Evaluated on real drone-recorded audio (SNR ranging from −35 to 0 dB), this method outperforms existing deep learning-based speech enhancement methods in three metrics: SNR improvement, short-time objective intelligibility (STOI), and perceptual evaluation of speech quality (PESQ), demonstrating superior performance in extreme noise scenario.
Zitieren
APA
Wei, Y., Zhang, J. A., Yen, B., & Hioka, Y. (2025). Spatial-U-Net: A multi-channel speech enhancement framework for low signal-to-noise ratio scenario. The Journal of the Acoustical Society of America, 158(4_Supplement), A475-A475. https://doi.org/10.1121/10.0041587
Vancouver
Wei Y, Zhang JA, Yen B, Hioka Y. Spatial-U-Net: A multi-channel speech enhancement framework for low signal-to-noise ratio scenario. The Journal of the Acoustical Society of America. 2025;158(4_Supplement):A475-A475. doi:10.1121/10.0041587
BibTeX
@article{Wei2025,
author = {Wei, Yifei and Zhang, Jihui (Aimee) and Yen, Benjamin and Hioka, Yusuke},
title = {Spatial-U-Net: A multi-channel speech enhancement framework for low signal-to-noise ratio scenario},
journal = {The Journal of the Acoustical Society of America},
year = {2025},
volume = {158},
number = {4_Supplement},
pages = {A475--A475},
doi = {10.1121/10.0041587}
}
EUVIMED