Towards Voice Reconstruction from EEG during Imagined Speech

Authors

  • Young-Eun Lee Korea University, Seoul, Republic of Korea
  • Seo-Hyun Lee Korea University, Seoul, Republic of Korea
  • Sang-Ho Kim Korea University, Seoul, Republic of Korea
  • Seong-Whan Lee Korea University, Seoul, Republic of Korea

DOI:

https://doi.org/10.1609/aaai.v37i5.25745

Keywords:

HAI: Brain-Sensing and Analysis, CMS: Brain Modeling, HAI: Communication Protocols

Abstract

Translating imagined speech from human brain activity into voice is a challenging and absorbing research issue that can provide new means of human communication via brain signals. Efforts to reconstruct speech from brain activity have shown their potential using invasive measures of spoken speech data, but have faced challenges in reconstructing imagined speech. In this paper, we propose NeuroTalk, which converts non-invasive brain signals of imagined speech into the user's own voice. Our model was trained with spoken speech EEG which was generalized to adapt to the domain of imagined speech, thus allowing natural correspondence between the imagined speech and the voice as a ground truth. In our framework, an automatic speech recognition decoder contributed to decomposing the phonemes of the generated speech, demonstrating the potential of voice reconstruction from unseen words. Our results imply the potential of speech synthesis from human EEG signals, not only from spoken speech but also from the brain signals of imagined speech.

Downloads

Published

2023-06-26

How to Cite

Lee, Y.-E., Lee, S.-H., Kim, S.-H., & Lee, S.-W. (2023). Towards Voice Reconstruction from EEG during Imagined Speech. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5), 6030-6038. https://doi.org/10.1609/aaai.v37i5.25745

Issue

Section

AAAI Technical Track on Humans and AI