EUVIMEDEUVIMED entdecken
Crossref

Improved Encoder-Decoder Architecture With Human-Like Perception Attention for Monaural Speech Enhancement

Hao Zhou, Yi Zhou, Zhenhua Cheng, Yu Zhao, Yin Liu

IEEE Signal Processing Letters · 2025 · 32 · 1670-1674

DOI: 10.1109/lsp.2025.3558690 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Hao Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Key Research & Development (R&D) Program of China, National Natural Science Foundation of China, Natural Science Foundation of Chongqing, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech enhancement (SE) models based on deep neural networks (DNNs) have shown excellent denoising performance. However, mainstream SE models often have high structural complexity and large parameter sizes, requiring substantial computational resources, which limits their practical application. In this paper, a high-efficiency encoder-decoder structure, inspired by the top-down attention mechanism in human brain perception and named human-like perception attention network (HPANet), is proposed for monaural speech enhancement, which is able to emulate brain perceptual attention in noise environments. In HPANet, the raw waveform is first encoded by using attention encoder to capture shallow global features. These features are then downsampled, and multi-scale information is aggregated through top attention module to prevent the loss of crucial information. Next, down attention module integrates features from neighboring layers to reconstruct signal in a top-down manner. Finally, the decoder reconstructs the denoised clean signal. Experiments show that the proposed method effectively reduces model complexity while maintaining competitive performance.

Förderung

  • National Key Research & Development (R&D) Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Chongqing, China

Zitieren

APA

Zhou, H., Zhou, Y., Cheng, Z., Zhao, Y., & Liu, Y. (2025). Improved Encoder-Decoder Architecture With Human-Like Perception Attention for Monaural Speech Enhancement. IEEE Signal Processing Letters, 32, 1670-1674. https://doi.org/10.1109/lsp.2025.3558690

Vancouver

Zhou H, Zhou Y, Cheng Z, Zhao Y, Liu Y. Improved Encoder-Decoder Architecture With Human-Like Perception Attention for Monaural Speech Enhancement. IEEE Signal Processing Letters. 2025;32:1670-1674. doi:10.1109/lsp.2025.3558690

BibTeX
@article{Zhou2025,
  author = {Zhou, Hao and Zhou, Yi and Cheng, Zhenhua and Zhao, Yu and Liu, Yin},
  title = {Improved Encoder-Decoder Architecture With Human-Like Perception Attention for Monaural Speech Enhancement},
  journal = {IEEE Signal Processing Letters},
  year = {2025},
  volume = {32},
  pages = {1670--1674},
  doi = {10.1109/lsp.2025.3558690}
}
Kostenlos starten →