Towards Neural Decoding of Imagined Speech based on Spoken Speech

TL;DR

This study explores whether spoken speech brain signals can be used to decode imagined speech, showing promising results that suggest shared neural features, which could advance silent communication technologies.

Contribution

It demonstrates the feasibility of transferring models trained on spoken speech EEG data to decode imagined speech, highlighting shared neural features between the two.

Findings

Transferred spoken speech classifier achieved 26.8% accuracy on imagined speech data.

No significant difference between imagined speech trained classifier and transferred classifier (p=0.0983).

Visual imagery data showed a significant difference between trained and transferred performance (p=0.022).

Abstract

Decoding imagined speech from human brain signals is a challenging and important issue that may enable human communication via brain signals. While imagined speech can be the paradigm for silent communication via brain signals, it is always hard to collect enough stable data to train the decoding model. Meanwhile, spoken speech data is relatively easy and to obtain, implying the significance of utilizing spoken speech brain signals to decode imagined speech. In this paper, we performed a preliminary analysis to find out whether if it would be possible to utilize spoken speech electroencephalography data to decode imagined speech, by simply applying the pre-trained model trained with spoken speech brain signals to decode imagined speech. While the classification performance of imagined speech data solely used to train and validation was 30.5 %, the transferred performance of spoken speech based classifier to imagined speech data displayed average accuracy of 26.8 % which did not have statistically significant difference compared to the imagined speech based classifier (p = 0.0983, chi-square = 4.64). For more comprehensive analysis, we compared the result with the visual imagery dataset, which would naturally be less related to spoken speech compared to the imagined speech. As a result, visual imagery have shown solely trained performance of 31.8 % and transferred performance of 26.3 % which had shown statistically significant difference between each other (p = 0.022, chi-square = 7.64). Our results imply the potential of applying spoken speech to decode imagined speech, as well as their underlying common features.