EEG
This page groups the current SSI review database by the real `modality:` tag `modality:eeg`.
The list below includes every paper page that currently carries this technique label.
Papers
AESSI: An Around-Ear Silent Speech Interface for Cross-Day Online Reuse without Test-Day Calibration
耳周囲cEEGridで25の固定中国語文を認識。テスト日較正なしの別日ホルドアウトで平均92.24%、21日以上後のライブ250試行で98.00%。開語彙会話や患者適用は未実証。
Do EEG Foundation Models Transfer to Speech? A Benchmark on Overt and Imagined Speech Decoding
General EEG pretraining shows no consistent speech-decoding advantage here; word decoding remains weak, and test-subject-informed early stopping limits the unseen-user claim.
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
Introducing PNA, the paper advances non-invasive brain-to-speech decoding by creating artifact-informed augmentations via ICA, significantly improving imagined speech classification accuracy on MEG data when combined with trial averaging.
EEG-Based Imagined Speech Decoding Using a Hybrid CNN-SNN Architecture
Promising five-class EEG classification at a reported 80.13% accuracy; independent replication, a matched spiking ablation, and actual power and online tests remain necessary.
A 1000-hour EEG-EMG-audio dataset of Japanese speech production
A 1020-hour multimodal EEG-EMG-audio dataset for Japanese overt speech vastly expands data resources, enabling diverse speech decoding and EEG research, though generalization is limited by three participants and no decoding benchmarks are presented.
Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
Offers useful activation-intervention diagnostics, but donor replacement bypasses recipient information, baseline/patch scores are unresolved, and winner counts exceed the stated layer width; strong causal conclusions are not established.
EEG-to-Voice Decoding of Spoken and Imagined speech Using Non-Invasive EEG
Subject-specific EEG reconstructs known cued utterances offline, but imagined-speech WER remains 47.48% at 2 s and 43.46% at 4 s before correction; unseen content, real-time use and fully alignment-free processing are not demonstrated.
MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding
想像発話11クラスの未学習者正解率は混合あり12.12%でEEGNetの10.61%から小幅改善。ただし本人の較正が必要で、拡散モデルなしの構成も上回るため、較正不要の実用的な発話認識とはいえない。
Subject-Independent Imagined Speech Detection via Cross-Subject Generalization and Calibration
6人の脳波で想像発話と休止を区別し、本人の学習用標本10%で較正すると正解率は67.0%から78.1%へ改善。単語の解読ではなく発話状態の検出であり、較正不要の汎化や実利用は未実証。
CAT-Net: A Cross-Attention Tone Network for Cross-Subject EEG-EMG Fusion Tone Decoding
脳波と筋電を組み合わせ、声を出さずに発音した中国語の四声を分類する研究。学習に含まない人で平均85.10%を報告するが、文章認識ではなく、指標名や分割・チャネル選択手順には確認が必要。
Toward Practical BCI: A Real-time Wireless Imagined Speech EEG Decoding System
想像した4命令を脳波で分類する試作系を有線・無線で実装し、正解率は62.00%と46.67%。本人の較正が必要で、3人・分割不明の評価から日常利用や自由な文章の解読まで実証したとはいえない。
Lightweight Diffusion-based Framework for Online Imagined Speech Decoding in Aphasia
失語症のある1人で、想像する3語と休止の実時間分類を試作。著者報告は第1候補65%・上位2候補70%だが、クラス別値と集計が整合せず、性能の確定には原データの確認が必要。
Distinct Theta Synchrony across Speech Modes: Perceived, Spoken, Whispered, and Imagined
健康な10人の脳波で、聞く・有声発話・ささやき・想像発話の同期分布を比較する基礎研究。認識精度は測らず、有意差や予測性能を裏付ける詳細も不足している。
Reconstructing Unseen Sentences from Speech-related Biosignals for Open-vocabulary Neural Communication
Held-out sentence reconstruction is demonstrated in personalized EEG/EMG experiments, but the strongest aggregate evidence is overt/whispered phoneme decoding—not unrestricted imagined-speech communication.
NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training
課題別の補助学習とテスト時適応により、本人内の5種類の想像発話分類を改善する研究。CBraModのBalanced Accuracyは58.98%だが、未知被験者への想像発話適用は偶然水準で、自由文や較正不要のSSIではない。
A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations
電極配置の違う脳波・筋電データの統合学習は64語分類を改善するが、患者1人の本人別評価であり、別日・自由な会話・臨床効果への隔たりが残る。
Towards Neural Decoding of Imagined Speech based on Spoken Speech
Transfer of CSP+SVM models trained on spoken speech EEG to imagined speech achieves comparable, though slightly lower, accuracy within a limited 5-class, 7-subject offline EEG setup, with visual imagery control supporting specificity.
A comparison of oscillatory characteristics in covert speech and speech perception
Strong covert-speech EEG analysis, not an SSI system.
Continuous Silent Speech Recognition using EEG
Real EEG sentence-level silent speech recognition is demonstrated but at very high WER, confirming feasibility only and underscoring the immature state of current EEG silent speech technology.
A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method
Useful EEG-SSR corpus framing paper, but evidence is lighter than a full benchmark paper.