The Potential for a Speech Brain–Computer Interface Using Chronic Electrocorticography

Abstract

A brain-computer interface (BCI) is a technology that uses neural features to restore or augment the capabilities of its user. A BCI for speech would enable communication in real time via neural correlates of attempted or imagined speech. Such a technology would potentially restore communication and improve quality of life for locked-in patients and other patients with severe communication disorders. There have been many recent developments in neural decoders, neural feature extraction, and brain recording modalities facilitating BCI for the control of prosthetics and in automatic speech recognition (ASR). Indeed, ASR and related fields have developed significantly over the past years, and many lend many insights into the requirements, goals, and strategies for speech BCI. Neural speech decoding is a comparatively new field but has shown much promise with recent studies demonstrating semantic, auditory, and articulatory decoding using electrocorticography (ECoG) and other neural recording modalities. Because the neural representations for speech and language are widely distributed over cortical regions spanning the frontal, parietal, and temporal lobes, the mesoscopic scale of population activity captured by ECoG surface electrode arrays may have distinct advantages for speech BCI, in contrast to the advantages of microelectrode arrays for upper-limb BCI. Nevertheless, there remain many challenges for the translation of speech BCIs to clinical populations. This review discusses and outlines the current stateof-the-art for speech BCI and explores what a speech BCI using chronic ECoG might entail.

Characterization of transection spinal cord injuries by monitoring somatosensory evoked potentials and motor behavior

“…Electroencephalography (EEG) and its many variants such as electrocorticography (ECoG), somatosensory evoked potential (SSEP), and magnetoencephalography (MEG) have been proven valuable for CNS assessment and monitoring. They have shown promise in evaluation and assessments of SCI as well (Rabbani et al, 2019;Al-Nashash et al, 2009;Agrawal et al, 2010a). SSEP is a clinical neuro-electrophysiological tool used to assess the onset and progress of neuronal injuries.…”

Silent Speech Interfaces for Speech Restoration: A Review

“…Such recordings have a time resolution of less than a millisecond, can be modelled reliably and are well understood [195]. When these potentials are recorded using non-invasive electrodes from the scalp they are known as EEG; or as electrocorticography (ECoG) when they are recorded from the cerebral cortex using invasive subdural grid electrodes [196]; or as local field potentials (LFPs) when the measurement is obtained at deeper locations by inserting electrodes or probes [194]. Alternatively, currents generated by the neurons can be measured non-invasively outside the skull as ultra-weak magnetic fields.…”

“…Invasive techniques, such as ECoG and LFPs, despite the evident risks they pose, seem a more promising alternative for chronic implantation as the basis of a neural speech prosthesis [196]. One such device is a probe designed at the University of Michigan [200], which is constructed on a silicon wafer using a photolithography process to pattern the interconnects and recording sites.…”

A New Era for Surgical Neurotherapeutics

“…Addressing vision restoration, Niketeghad and Pouratian [18] describe the historical thinking on cortical visual prosthetics, as well as the current state of the art, explaining the design of current devices that are either under development or in the clinical testing phase. Rabbani and colleagues [19] then complete this section by introducing us to the field of neural speech decoding using electrocorticography, exploring what a brain-computer interface for speech might entail.…”