Brain-computer interface (BCI)-generated speech to control domotic devices

• Published in: Neurocomputing (Amsterdam) 2022-10, Vol.509, p.121-136
• Main Authors: Velasco-Álvarez, Francisco, Fernández-Rodríguez, Álvaro, Ron-Angevin, Ricardo
• Format: Article
• Language: English
• Subjects: Assistive technology; Brain-computer interface (BCI); Domotic; Event-related potential (ERP); Speech generation; Virtual assistant
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2022.08.068

A brain-computer interface (BCI) is a type of technology that establishes a communication channel between a user and certain devices in the environment via the brain signals of the user. The UMA-BCI Speller tool allows for easy configuration of a BCI, permitting it to be manipulated without the need for much technical knowledge. However, adapting a BCI system so that it can communicate with devices is a challenging task. A simpler technology that is increasingly used to enable communication with devices in the environment is based on voice commands. The aim of the present work is therefore to create a system to facilitate communication between a BCI and devices in the environment using voice commands. Twelve healthy participants and three amyotrophic lateral sclerosis (ALS) patients were asked to control a BCI home automation system. The devices to be controlled were a television, an air conditioner, a smart light bulb, a smart plug, and the WhatsApp and Spotify apps. Performance measures were recorded, and subjective measures were collected based on the System usability scale, NASA-TLX and ad hoc questionnaires. The results of this study validate the proposed system as a suitable option to facilitate communication between a BCI and commercial devices that have been previously adapted to operate based on voice commands.