---
title: "HFFN-ID: A Hierarchical Feature Fusion Network with Bi-Phase Subject ID Modulation for EEG Mel-Spectrogram Reconstruction"
authors:
  - "Chi Huang"
  - "Zhaohu Liu"
  - "Yong Peng"
  - "Wanzeng Kong"
doi: "10.24963/ijcai.2026/402"
url: "https://ijcai.org/proceedings/2026/402"
pdf: "https://ijcai.org/proceedings/2026/0402.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3612-3620"
track: "Main Track"
keywords:
  - "Humans and AI: Human-computer interaction"
  - "Humans and AI: Cognitive modeling"
  - "Humans and AI: Intelligent user interfaces"
---

# HFFN-ID: A Hierarchical Feature Fusion Network with Bi-Phase Subject ID Modulation for EEG Mel-Spectrogram Reconstruction

Chi Huang, Zhaohu Liu, Yong Peng, Wanzeng Kong

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3612-3620. DOI: [10.24963/ijcai.2026/402](https://doi.org/10.24963/ijcai.2026/402)

## Abstract

High-fidelity reconstruction of mel-spectrograms from EEG signals remains a formidable challenge, primarily due to the inherent inter-subject variability of neural patterns and the semantic gap between heterogeneous feature representations of these two modalities. To alleviate both issues, this paper proposes a Hierarchical Feature Fusion Network with bi-phase subject IDentifier modulation (HFFN-ID) for reconstructing mel-spectrograms from EEG signals. The primary improvements of the HFFN-ID framework are from two aspects, a Binary-Phase Subject-ID Modulation (BiPSM) mechanism for explicit subject conditioning and a Condition-guided Hierarchical Fusion (CHF) component for dynamic multi-layer feature synthesis, which respectively aim to address the problems of inter-subject variability in neural patterns and heterogeneous cross-modality feature fusion. Moreover, a speech envelope feature-based pre-training strategy is incorporated to initialize the parameter space, inspired by the shared low-level representations across different speech features. On the SparrKULee dataset, HFFN-ID establishes a new benchmark with a pearson correlation coefficient of 0.0723, representing a substantial 44% relative improvement over existing baseline. Importantly, HFFN-ID is highly efficient, achieving a 38.7% parameter reduction and a 2.5× training speedup. These results highlight the effectiveness of subject-conditioned and hierarchically fused architectures for advancing high-fidelity neural speech decoding.