收藏切换
GALENet: Neuro-Oriented Speaker Extraction Network Fusing Gated Attention and Local Feature Enhancement
收藏切换
Cunhang Fan1, Junling Li1, Jingjing Zhang1, Youdian Gao1, Ying Chen1, Jiangyan Yi2, Zhao Lü1, *
Journal of Computer Research and Development | 2026, 63(6) : 1534 - 1547
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(6): 1534-1547
• Artificial Intelligence •
GALENet: Neuro-Oriented Speaker Extraction Network Fusing Gated Attention and Local Feature Enhancement
Full
Cunhang Fan1, Junling Li1, Jingjing Zhang1, Youdian Gao1, Ying Chen1, Jiangyan Yi2, Zhao Lü1, *
Affiliations
  • 1State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology (Anhui University), Hefei 230601
  • 2Department of Automation, Tsinghua University, Beijing 100084
  • born in 1991. PhD, associate professor, master supervisor. His main research interests include speech information processing, brain-computer interface technology, and brain-inspired auditory computing

    born in 2002. Master candidate. His main research interests include speech separation and brain-controlled target speaker extraction

    born in 2000. Master. Her main research interests include speech separation and brain-controlled target speaker extraction

    born in 2001. Master candidate. His main research interests include audio-visual speech separation and target speaker extraction

    born in 2001. Master candidate. Her main research interests include speech separation and brain-controlled target speaker extraction

    born in 1984. PhD, assistant professor. Her main research interests include speech recognize, and speech synthesis and transfer learning

    born in 1979. PhD, professor, PhD supervisor. His main research interests include emotion recognition, speech enhancement, and motor imagery

About Author:

born in 1991. PhD, associate professor, master supervisor. His main research interests include speech information processing, brain-computer interface technology, and brain-inspired auditory computing

born in 2002. Master candidate. His main research interests include speech separation and brain-controlled target speaker extraction

born in 2000. Master. Her main research interests include speech separation and brain-controlled target speaker extraction

born in 2001. Master candidate. His main research interests include audio-visual speech separation and target speaker extraction

born in 2001. Master candidate. Her main research interests include speech separation and brain-controlled target speaker extraction

born in 1984. PhD, assistant professor. Her main research interests include speech recognize, and speech synthesis and transfer learning

born in 1979. PhD, professor, PhD supervisor. His main research interests include emotion recognition, speech enhancement, and motor imagery

Published: 2026-06-01 doi: 10.7544/issn1000-1239.202550467
Outline
收藏切换

Neuro-oriented speaker extraction is an intelligent speech processing technique that emulates human auditory attention mechanisms, enabling target speaker extraction from mixed speech by decoding the attentional focus embedded in listeners’ EEG (electroencephalogram) signals. This technology offers novel insights into resolving the “cocktail party problem” and holds significant implications for developing intelligent hearing-assistive devices. However, existing approaches confront three critical challenges: inefficient multimodal feature fusion, inadequate local speech feature extraction, and high computational complexity, which collectively constrain practical application efficacy. We propose GALENet, a novel end-to-end time-domain speaker extraction model, featuring three innovative modules: 1) A gated cross-attention fusion mechanism that establishes cross-modal correlations between EEG and speech through bidirectional cross-attention, while adaptively modulating modal contributions via dynamic gating weights to overcome the information interaction limitations of conventional linear fusion; 2) An E-DPRNN network incorporating Conv-U modules within the dual-path architecture to reinforce local short-term feature capture, synergized with residual connections to enhance gradient propagation efficiency; 3) A single-path global modulation (SPGM) block that replaces traditional inter-block modeling with parameter-free pooling and feature modulation, preserves global semantic modeling capability while reducing parameters. These modules collectively achieve efficient multimodal fusion and precise speaker extraction. Experimental validation demonstrates that the proposed method attains average SI-SDR scores of 13.59 dB, 10.44 dB, and 10.17 dB on the Cocktail Party, AVED, and MM-AAD datasets respectively, outperforming the baseline model MSFNet by 5.4%−8.2% while reducing parameters by 49.7%−55.6%. These results substantiate the model’s application potential and effectiveness in neuro-oriented speaker extraction.

neuro-oriented speaker extraction  /  EEG signals  /  multimodal fusion  /  gated cross-attention  /  speech separation  /  end-to-end learning
范存航, 李骏凌, 张晶晶, 高佑典, 陈颖, 易江燕, 吕钊. GALENet:融合门控注意力与局部特征增强的神经导向说话人提取网络. 计算机研究与发展, 2026 , 63 (6) : 1534 -1547 . DOI: 10.7544/issn1000-1239.202550467
Cunhang Fan, Junling Li, Jingjing Zhang, Youdian Gao, Ying Chen, Jiangyan Yi, Zhao Lü. GALENet: Neuro-Oriented Speaker Extraction Network Fusing Gated Attention and Local Feature Enhancement[J]. Journal of Computer Research and Development, 2026 , 63 (6) : 1534 -1547 . DOI: 10.7544/issn1000-1239.202550467
Year 2026 volume 63 Issue 6
83
38
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550467
  • Receive Date:2025-06-09
  • Online Date:2026-11-17
  • Published:2026-06-01
Article Data
Affiliations
History
  • Received:2025-06-09
  • Revised:2026-01-16
  • Accepted:2026-01-29
Affiliations
    1State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology (Anhui University), Hefei 230601
    2Department of Automation, Tsinghua University, Beijing 100084
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550467
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT