aiqbench analysis
This research advances non-invasive brain-computer interfaces by introducing a CPSD framework that leverages contrastive learning and spatial attention to improve cross-subject generalization in decoding perceived speech from MEG/EEG data. By separating shared neural representations from subject-specific variations, the method significantly reduces training costs while boosting Top-10 accuracy across diverse datasets and languages. This work represents a critical step toward practical, scalable BCI applications for communication and assistive technologies.
Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings
arXiv:2608.22420v1 Announce Type: cross Abstract: Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential applications. However, existing methods face considerable challenges in cross-subject decoding, primarily due to limited generalizability and the absence of explicit mechanisms for extracting subject-consistent information. These limitations result in high training costs and suboptimal decoding performance. To address these challenges, we propose an innovative Cross-Subject Perceived Speech Decoding (CPSD) framework, which comprises two training stages: source model pre-training and personal specialization. In the source model pre-training stage, contrastive learning is employed to capture shared representations across multiple source subjects. Subsequently, personal specialization initializes the model for the target subject by extracting consistent components from the source model and fine-tuning it using target subject data. Additionally, we introduce the Positional Encoding-based Spatial Attention (PESA) module, which remaps MEG/EEG data into a standardized reference space, thereby enhancing cross-subject consistency and facilitating model training. We evaluate the proposed CPSD framework on three perceived speech neural datasets encompassing different modalities and languages. The results demonstrate that our framework outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top-10 accuracy on the Armeni 2022, PKUEEG 2025, and Broderick 2018 datasets, respectively. Further analyses confirm the effectiveness, efficiency, and robustness of the proposed approach.
Abstract:Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential applications. However, existing methods face considerable challenges in cross-subject decoding, primarily due to limited generalizability and the absence of explicit mechanisms for extracting subject-consistent information. These limitations result in high training costs and suboptimal decoding performance. To address these challenges, we propose an innovative Cross-Subject Perceived Speech Decoding (CPSD) framework, which comprises two training stages: source model pre-training and personal specialization. In the source model pre-training stage, contrastive learning is employed to capture shared representations across multiple source subjects. Subsequently, personal specialization initializes the model for the target subject by extracting consistent components from the source model and fine-tuning it using target subject data. Additionally, we introduce the Positional Encoding-based Spatial Attention (PESA) module, which remaps MEG/EEG data into a standardized reference space, thereby enhancing cross-subject consistency and facilitating model training. We evaluate the proposed CPSD framework on three perceived speech neural datasets encompassing different modalities and languages. The results demonstrate that our framework outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top-10 accuracy on the Armeni 2022, PKUEEG 2025, and Broderick 2018 datasets, respectively. Further analyses confirm the effectiveness, efficiency, and robustness of the proposed approach.
Sound (cs.SD); Artificial Intelligence (cs.AI)
arXiv:2608.22420 [cs.SD]
(or arXiv:2608.22420v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2608.22420 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 307 words
Related coverage
Subject-Invariant Cross-Modal Decoding of Perceived Speech from Brain Recordings
arXiv · Sep 28, 2026
Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning
arXiv · Jul 23, 2026
Cross-subject decoding of imagined speech from scalp EEG: a leakage-controlled evaluation on three public corpora
arXiv · Oct 16, 2026
[AINews] not much happened today
Latent Space · Oct 3, 2026