EUVIMEDEUVIMED entdecken
Open Access

Real-time decoding of full-spectrum Chinese using brain-computer interface

Youkun Qian iD, Changjiang Liu iD, Peixi Yu iD, Xingchen Ran iD, Shurui Li iD, Qinrong Yang iD, Yang Liu, Lei Xia, Yijie Wang, Jianxuan Qi iD, Erda Zhou iD, Junfeng Lu iD und 4 weitere

Science Advances · 07.11.2025 · 11 (45)

DOI: 10.1126/sciadv.adz9968 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 07.11.2025. Verfasst von Youkun Qian und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai 200040, China. Hauptthemen laut MEDLINE: Brain-Computer Interfaces, Speech. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech brain-computer interfaces (BCIs) offer a promising means to provide functional communication capacity for patients with anarthria caused by neurological conditions such as amyotrophic lateral sclerosis (ALS) or brainstem stroke. Current speech decoding research has predominantly focused on English using phoneme-driven architectures, whereas real-time decoding of tonal monosyllabic languages such as Mandarin Chinese remains a major challenge. This study demonstrates a real-time Mandarin speech BCI that decodes monosyllabic units directly from neural signals. Using the 256-channel microelectrocorticographic BCI, we achieved robust decoding of a comprehensive set of 394 distinct syllables based purely on neural signals, yielding median syllable identification accuracy of 71.2% in a single-character reading task. Leveraging this high-performing syllable decoder, we further demonstrated real-time sentence decoding. Our findings demonstrate the efficacy of a tonally integrated, direct syllable neural decoding approach for Mandarin Chinese, paving the way for full-coverage systems in tonal monosyllabic languages.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain-Computer InterfacesSpeechHumansLanguageMaleFemaleAdultElectroencephalographyChinaEast Asian People

Autor:innen und Institutionen

  • Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai 200040, China.
  • Shanghai Key Laboratory of Clinical and Translational Brain-Computer Interface Research, Shanghai 200040, China.
  • National Center for Neurological Disorders, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai 200040, China.
  • 2020 X-Lab, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, China.
  • School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China.
  • State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai 201210, China.

ORCID-Profile: Youkun Qian, Changjiang Liu, Peixi Yu, Xingchen Ran, Shurui Li, Qinrong Yang, Jianxuan Qi, Erda Zhou, Junfeng Lu, Yuanning Li, Zhitao Zhou, Jinsong Wu

Zitieren

APA

Qian, Y., Liu, C., Yu, P., Ran, X., Li, S., Yang, Q., Liu, Y., Xia, L., Wang, Y., Qi, J., Zhou, E., Lu, J., Li, Y., Tao, T. H., Zhou, Z., & Wu, J. (2025). Real-time decoding of full-spectrum Chinese using brain-computer interface. Science Advances, 11(45). https://doi.org/10.1126/sciadv.adz9968

Vancouver

Qian Y, Liu C, Yu P, Ran X, Li S, Yang Q, et al. Real-time decoding of full-spectrum Chinese using brain-computer interface. Science Advances. 2025;11(45). doi:10.1126/sciadv.adz9968

BibTeX
@article{Qian2025,
  author = {Qian, Youkun and Liu, Changjiang and Yu, Peixi and Ran, Xingchen and Li, Shurui and Yang, Qinrong and Liu, Yang and Xia, Lei and Wang, Yijie and Qi, Jianxuan and Zhou, Erda and Lu, Junfeng and Li, Yuanning and Tao, Tiger H and Zhou, Zhitao and Wu, Jinsong},
  title = {Real-time decoding of full-spectrum Chinese using brain-computer interface},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {45},
  doi = {10.1126/sciadv.adz9968}
}
Kostenlos starten →