کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

BrainTranslator: Decoding Coherent Text from EEG Signals with Scheduled Sampling

نویسندگان :

Fatemeh Majidi¹ Mohammad Bagher Khodabakhshi² Mohammad Reza Rezaeian³

1- hamedan university of technology 2- hamedan university of technology 3- hamedan university of technology

کلمات کلیدی :

EEG-to-Text،Transformer،BrainTranslator،Scheduled Sampling،Brain–Computer Interface (BCI)

چکیده :

In recent years, converting EEG signals directly into natural text has become a major challenge in brain–computer interfaces. This study presents BrainTranslator, a Transformer-based model that generates coherent sentences directly from neural activity. The architecture includes an EEG encoder and a BART-based decoder. The encoder produces word-level and sentence-level representations; the sentence-level vector is derived through temporal mean pooling as an 840-dimensional feature and is placed at the start of the sequence. The decoder generates text after a linear projection layer (840 to 1024). Training follows a two-stage procedure. First, the EEG encoder is trained while the decoder remains fixed. Then, the full network is optimized end-to-end. Scheduled Sampling is applied to create realistic generation conditions and reduce Exposure Bias. The model is evaluated in an inter-subject setting using the ZuCo dataset. Results indicate that even under fully generative conditions (without Teacher Forcing), BrainTranslator achieves BLEU-1 of 0.4372, BLEU-4 of 0.0911, and a CER of 1.21. Accuracy is higher for key lexical items and short syntactic patterns than for longer sequences. Overall, BrainTranslator offers an effective framework for direct EEG-to-text decoding and supports progress in assistive communication technologies and next-generation brain–computer interfaces.

لیست مقالات

لیست مقالات بایگانی شده

A New High Voltage Gain Z-Source Based DC-DC Converter for High-Power DG Applications

Sakina Bakhshi - Reza Beiranvand

Graphene-Based Slot Antenna with Improved Bandwidth for 6G Terahertz Communications

Alireza Tahvildari - Aslan Nouri Moqadam - Shokrollah Karimian

Average Secrecy Capacity Performance Analysis for SWIPT-Based SIMO Underlay Cognitive Radio

Mohammad Javad Saber1 - Seyedeh Maryam Mazloum - Seyed Mohammad Sajad Sadough

Unsupervised Change Detection in SAR Images Using a Six-Branch CNN and Adaptive Window Approach

Abbas Kakoolvand - Maryam Imani - Hassan Ghassemian

A Fast Approach for Deep Neural Network Implementation on FPGA

Maedeh Nobari - Hadi Jahanirad

Comparison of the MRT and ZF Precoding in Massive MIMO Systems from Energy Efficiency Viewpoint

Mahdi Nangir - Abdolrasoul Sakhaei Gharagezlou - Nima Imani

Does Lower Extremity Rehabilitation Affect The Recurrence Dynamics of Hand EMG Signals? A Case Study

Shahed Salehzehi - Parisa Hosseini - Zahra Alizadeh Sarborj - Mobina Ramezani - Ahmadreza Borna - Mobina Hemati - Hamid Reza Kobravi - Mehran Beiraghi Toosi - Narges Hashemi - Javad Akhondian

Crypto Currency Price Prediction Using Preprocessed Scaled Inputs LSTM Model Enhanced by Improved Gray Wolf Optimization

Amir RabbaniParsa - Mahboobeh Hoshmand - Seyyed Abed Hosseini

Investigating the Effects of Adding Distributed Generation Resources to the Distribution Networks on their Protection System Performance

Morteza Abbasghorbani - Elham Vahed

Integration of Deep Learning Techniques in Stock Market Forecasting: xLSTM-CNN with RevIN and Adaptive Wavelet Denoising

Alireza Mohammadi - Ali Doustmohammadi - Masoud Shafiee

بیشتر