Akito Yoshida
Akito Yoshida has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Kenichi Tomeoka
Araya Inc
2 shared publications Mayumi Shimizu
Araya Inc
2 shared publications- Motoshige Sato
Araya Inc
2 shared publications - Shuntaro Sasai
Araya Inc
2 shared publications Yasuo Kabe
Araya Inc
2 shared publications- Atsushi Yamamoto
Araya Inc
1 shared publication
Latest Publications
- Open Access
- 1 October 2026
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 23 (5) , 056062
Delineating neural contributions to electroencephalogram-based speech decoding
Objective . Speech brain–computer interfaces (BCIs) have emerged as a pivotal technology in facilitating communication for individuals with speech impairments. Utilizing electroencephalography (EEG) for noninvasive speech BCIs offers an accessible and affordable solution, potentially benefiting a broader audience. However, EEG-based speech decoding remains controversial especially for overt speech, due to difficulties in separating speech-related neural activities from myoelectric potential artifacts generated during articulation. Moreover, because paradigms for collecting covert speech data are inherently less scalable than those for overt speech, whether the neural dynamics underlying EEG-based decoding of overt speech are also present during covert speech remains an open and practically important question. Approach . Here we aim to delineate the extent of the neural contributions to EEG-based speech decoding, and the degree to which the underlying neural dynamics are shared across overt and covert speech, by employing Explainable AI techniques to a convolutional neural network predicting spoken words based on signals obtained by ultra-high-density (uhd)-EEG. Main results . We found that electrode-wise contributions to the decoding cannot be explained by their mutual information with electromyography (EMG). Furthermore, contributing periods of speech to EEG-based decoding are distinct from those to decoding solely relying on EMG. Contributing periods of EEG-based decoding partially overlapped between overt and minimally overt speech. Notably, the denoising process successfully enhanced the decoding contribution from electrodes within speech-related brain areas for all speech conditions. Significance . Altogether, our findings support the idea that, with appropriate preprocessing, EEG becomes a valuable tool for decoding spoken words based on underlying neural activities.
- 1 October 2026
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 23 (5) , 056062
Open AccessDelineating neural contributions to electroencephalogram-based speech decoding
Objective . Speech brain–computer interfaces (BCIs) have emerged as a pivotal technology in facilitating communication for individuals with speech impairments. Utilizing electroencephalography (EEG) for noninvasive speech BCIs offers an accessible and affordable solution, potentially benefiting a broader audience. However, EEG-based speech decoding remains controversial especially for overt speech, due to difficulties in separating speech-related neural activities from myoelectric potential artifacts generated during articulation. Moreover, because paradigms for collecting covert speech data are inherently less scalable than those for overt speech, whether the neural dynamics underlying EEG-based decoding of overt speech are also present during covert speech remains an open and practically important question. Approach . Here we aim to delineate the extent of the neural contributions to EEG-based speech decoding, and the degree to which the underlying neural dynamics are shared across overt and covert speech, by employing Explainable AI techniques to a convolutional neural network predicting spoken words based on signals obtained by ultra-high-density (uhd)-EEG. Main results . We found that electrode-wise contributions to the decoding cannot be explained by their mutual information with electromyography (EMG). Furthermore, contributing periods of speech to EEG-based decoding are distinct from those to decoding solely relying on EMG. Contributing periods of EEG-based decoding partially overlapped between overt and minimally overt speech. Notably, the denoising process successfully enhanced the decoding contribution from electrodes within speech-related brain areas for all speech conditions. Significance . Altogether, our findings support the idea that, with appropriate preprocessing, EEG becomes a valuable tool for decoding spoken words based on underlying neural activities.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Motion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Open AccessMotion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions
- Open Access
Delineating neural contributions to electroencephalogram-based speech decoding
Speech Brain-computer interfaces (BCIs) have emerged as a pivotal technology in facilitating communication for individuals with speech impairments. Utilizing electroencephalography (EEG) for noninvasive speech BCIs offers an accessible and affordable solution, potentially benefiting a broader audience. However, EEG-based speech decoding remains controversial especially for overt speech, due to difficulties in separating speech-related neural activities from myoelectric potential artifacts generated during articulation. Here we aim to delineate the extent of the neural contributions by employing Explainable AI techniques to a convolutional neural network predicting spoken words based on signals obtained by ultra-high-density (uhd)-EEG. We found that electrode-wise contributions to the decoding cannot be explained by their mutual information with electromyography (EMG). Furthermore, contributing periods of speech to EEG-based decoding are distinct from those to decoding solely relying on EMG. In contrast, there are significant overlaps in signal timings contributing to EEG-based decoding, regardless of vocal conditions such as overt or covert speech. Notably, the denoising process successfully enhanced the decoding contribution from electrodes within speech-related brain areas for all speech conditions. Altogether, our findings support the idea that, with appropriate preprocessing, EEG becomes a valuable tool for decoding spoken words based on underlying neural activities.
Open AccessDelineating neural contributions to electroencephalogram-based speech decoding
Speech Brain-computer interfaces (BCIs) have emerged as a pivotal technology in facilitating communication for individuals with speech impairments. Utilizing electroencephalography (EEG) for noninvasive speech BCIs offers an accessible and affordable solution, potentially benefiting a broader audience. However, EEG-based speech decoding remains controversial especially for overt speech, due to difficulties in separating speech-related neural activities from myoelectric potential artifacts generated during articulation. Here we aim to delineate the extent of the neural contributions by employing Explainable AI techniques to a convolutional neural network predicting spoken words based on signals obtained by ultra-high-density (uhd)-EEG. We found that electrode-wise contributions to the decoding cannot be explained by their mutual information with electromyography (EMG). Furthermore, contributing periods of speech to EEG-based decoding are distinct from those to decoding solely relying on EMG. In contrast, there are significant overlaps in signal timings contributing to EEG-based decoding, regardless of vocal conditions such as overt or covert speech. Notably, the denoising process successfully enhanced the decoding contribution from electrodes within speech-related brain areas for all speech conditions. Altogether, our findings support the idea that, with appropriate preprocessing, EEG becomes a valuable tool for decoding spoken words based on underlying neural activities.
- 1 August 2023
- Published by Institute of Electrical Engineers of Japan (IEE Japan) in IEEJ Transactions on Industry Applications
- Vol. 143 (8) , 579-589
2重3相永久磁石同期モータの高調波電流低減のための巻線係数を用いた設計法検討
Dual three-phase motors offer numerous advantages, including the elimination of 6th-order torque ripple. However, they have the drawback of generating large harmonic currents when driven because of their small inductance for specific harmonics. In this study, inductance, which depends on the winding structure and harmonics, is formulated using the winding factor in order to reduce harmonic currents through winding design. The theoretical values of the formulated inductance are in good agreement with the FEA values. In addition, the magnitude of the harmonic currents generated during drive are quantitatively evaluated using these inductance values. Conventionally, when the winding factor for the 5th and 7th spatial harmonics is small, the 5th and 7th harmonics of back EMF can be reduced. However, dual three-phase motors with small winding factor for 5th and 7th spatial harmonics have the disadvantage of having very small inductance for specific harmonics, resulting in large harmonic currents.
- 1 August 2023
- Published by Institute of Electrical Engineers of Japan (IEE Japan) in IEEJ Transactions on Industry Applications
- Vol. 143 (8) , 579-589
2重3相永久磁石同期モータの高調波電流低減のための巻線係数を用いた設計法検討
Dual three-phase motors offer numerous advantages, including the elimination of 6th-order torque ripple. However, they have the drawback of generating large harmonic currents when driven because of their small inductance for specific harmonics. In this study, inductance, which depends on the winding structure and harmonics, is formulated using the winding factor in order to reduce harmonic currents through winding design. The theoretical values of the formulated inductance are in good agreement with the FEA values. In addition, the magnitude of the harmonic currents generated during drive are quantitatively evaluated using these inductance values. Conventionally, when the winding factor for the 5th and 7th spatial harmonics is small, the 5th and 7th harmonics of back EMF can be reduced. However, dual three-phase motors with small winding factor for 5th and 7th spatial harmonics have the disadvantage of having very small inductance for specific harmonics, resulting in large harmonic currents.