Toshihisa Tanaka

Interoceptive Accuracy Modulates Electroencephalogram During Music Recall Tasks

This study examines how interoceptive accuracy affects EEG patterns during music recall tasks, finding stronger alpha power suppression in individuals with higher interoceptive accuracy.

SleepSatelightFTC: A Lightweight and Interpretable Deep Learning Model for Single-Channel EEG-Based Sleep Stage Classification

The paper introduces SleepSatelightFTC, a lightweight deep learning model for EEG-based sleep stage classification that achieves high accuracy with fewer parameters and provides interpretability through self-attention.

Speech Synthesis from Electrocorticography during Imagined Speech Using a Transformer-Based Decoder and a Pretrained Vocoder

This paper synthesizes speech from imagined speech ECoG using a Transformer decoder and pre-trained vocoder, achieving high correlation with proxy targets.

Feasibility of decoding covert speech in ECoG with aTransformer trained on overt speech

This study uses a Transformer model trained on overt speech to decode covert speech from ECoG data, achieving similar performance to models trained directly on covert speech.

Partial Face Visibility and Facial Cognition: An Electroencephalography and Eye-Tracking Investigation

This paper investigates face cognition during the pandemic using EEG and eye-tracking, finding that eyes are critical for facial recognition and that partial face visibility can enhance cognition through visual working memory.

Effect of predicting familiar melodies on alpha power

This study investigates how familiar melodies affect alpha power, finding suppression in specific brain regions similar to language processing.

The Role of the Eyes: Investigating Face Cognition Mechanisms Using Machine Learning and Partial Face Stimuli

This paper uses machine learning to investigate face cognition mechanisms with partial face stimuli, finding that the eyes are the most effective component for cognitive processing.

Epileptic Spike Detection Using Neural Networks with Linear-Phase Convolutions

This paper introduces data-driven neural networks with linear-phase filters for detecting epileptic spikes in EEG data, achieving an average AUC of 0.967.