PCRNet: Phase-aware Complex Refinement Network for EEG-based Auditory Attention Decoding

Xiran Chen, Xiaoke Yang, Jian Zhou, Zhao Lv, Cunhang Fan
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:17866-17880, 2026.

Abstract

Auditory attention decoding (AAD) based on Electroencephalography (EEG) aims to identify the attended speaker in multi-speaker environments. However, existing methods typically overlook the crucial phase information of EEG signals, which limits their ability to distinguish structured neural patterns from random noise in the frequency domain and hinders robust decoding. To address these issues, this paper proposes a Phase-aware Complex Refinement Network (PCRNet) for AAD, which consists of a Temporal Context Calibration (TCC) module and a Dual-Domain Integration (DDI) module. Specifically, the TCC module captures long-range temporal dependencies through multi-scale temporal attention mechanism, while the DDI module employs a phase-guided spectral filtering strategy to dynamically suppress noise-dominated frequencies and refine the real and imaginary components separately. This design enables effective phase recalibration and enhances the discriminability of target features in the complex domain. Experimental results on three public datasets demonstrate that PCRNet outperforms state-of-the-art (SOTA) methods, particularly under challenging ultra-short 0.1-second windows. Code is available at: https://github.com/SunshineGreeny/PCRNet.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-chen26fr, title = {{PCRN}et: Phase-aware Complex Refinement Network for {EEG}-based Auditory Attention Decoding}, author = {Chen, Xiran and Yang, Xiaoke and Zhou, Jian and Lv, Zhao and Fan, Cunhang}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {17866--17880}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/chen26fr/chen26fr.pdf}, url = {https://proceedings.mlr.press/v306/chen26fr.html}, abstract = {Auditory attention decoding (AAD) based on Electroencephalography (EEG) aims to identify the attended speaker in multi-speaker environments. However, existing methods typically overlook the crucial phase information of EEG signals, which limits their ability to distinguish structured neural patterns from random noise in the frequency domain and hinders robust decoding. To address these issues, this paper proposes a Phase-aware Complex Refinement Network (PCRNet) for AAD, which consists of a Temporal Context Calibration (TCC) module and a Dual-Domain Integration (DDI) module. Specifically, the TCC module captures long-range temporal dependencies through multi-scale temporal attention mechanism, while the DDI module employs a phase-guided spectral filtering strategy to dynamically suppress noise-dominated frequencies and refine the real and imaginary components separately. This design enables effective phase recalibration and enhances the discriminability of target features in the complex domain. Experimental results on three public datasets demonstrate that PCRNet outperforms state-of-the-art (SOTA) methods, particularly under challenging ultra-short 0.1-second windows. Code is available at: https://github.com/SunshineGreeny/PCRNet.} }
Endnote
%0 Conference Paper %T PCRNet: Phase-aware Complex Refinement Network for EEG-based Auditory Attention Decoding %A Xiran Chen %A Xiaoke Yang %A Jian Zhou %A Zhao Lv %A Cunhang Fan %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-chen26fr %I PMLR %P 17866--17880 %U https://proceedings.mlr.press/v306/chen26fr.html %V 306 %X Auditory attention decoding (AAD) based on Electroencephalography (EEG) aims to identify the attended speaker in multi-speaker environments. However, existing methods typically overlook the crucial phase information of EEG signals, which limits their ability to distinguish structured neural patterns from random noise in the frequency domain and hinders robust decoding. To address these issues, this paper proposes a Phase-aware Complex Refinement Network (PCRNet) for AAD, which consists of a Temporal Context Calibration (TCC) module and a Dual-Domain Integration (DDI) module. Specifically, the TCC module captures long-range temporal dependencies through multi-scale temporal attention mechanism, while the DDI module employs a phase-guided spectral filtering strategy to dynamically suppress noise-dominated frequencies and refine the real and imaginary components separately. This design enables effective phase recalibration and enhances the discriminability of target features in the complex domain. Experimental results on three public datasets demonstrate that PCRNet outperforms state-of-the-art (SOTA) methods, particularly under challenging ultra-short 0.1-second windows. Code is available at: https://github.com/SunshineGreeny/PCRNet.
APA
Chen, X., Yang, X., Zhou, J., Lv, Z. & Fan, C.. (2026). PCRNet: Phase-aware Complex Refinement Network for EEG-based Auditory Attention Decoding. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:17866-17880 Available from https://proceedings.mlr.press/v306/chen26fr.html.

Related Material