A Non-Invasive Brain-Computer Interface for Real-Time Speech Synthesis: The Importance of Multimodal Feedback

Authors

Jonathan S. Brumberg, University of KansasFollow
Kevin M. Pitt, University of Nebraska - LincolnFollow
Jeremy D. Burnison, University of Kansas

ORCID IDs

Jonathan Brumberg https://orcid.org/0000-0001-5739-968X

Kevin Pitt https://orcid.org/0000-0003-3165-4093

Date of this Version

4-2018

Citation

Published in final edited form as: IEEE Trans Neural Syst Rehabil Eng. 2018 April ; 26(4): 874–881.

doi:10.1109/TNSRE.2018.2808425.

Comments

Author manuscript; available in PMC 2019 April 01.

Abstract

We conducted a study of a motor imagery brain-computer interface (BCI) using electroencephalography (EEG) to continuously control a formant frequency speech synthesizer with instantaneous auditory and visual feedback. Over a three-session training period, sixteen participants learned to control the BCI for production of three vowel sounds (/ℹ/[heed], /ɐ/[hot], and/u/[who’d]) and were split into three groups: those receiving unimodal auditory feedback of synthesized speech, those receiving unimodal visual feedback of formant frequencies, and those receiving multimodal, audio-visual feedback. Audio feedback was provided by a formant frequency artificial speech synthesizer and visual feedback was given as a two-dimensional cursor on a graphical representation of the plane defined by the first two formant frequencies. We found that combined audiovisual feedback led to the greatest performance in terms of percent accuracy, distance to target and movement time to target compared to either unimodal feedback of auditory or visual information. These results indicate that performance is enhanced when multimodal feedback is meaningful for the BCI task goals, rather than as a generic biofeedback signal of BCI progress.