Imagined Speech Reconstruction From Neural Signals-An Overview of Sources and Methods

Imagined speech, also known as inner, covert, or silent speech, means how to express thoughts silently without moving the vocal apparatus. Imagined speech reconstruction (ISR) refers to the innovative process of decoding and reconstructing the imagined speech in the human brain, using kinds of neural signals and advanced signal processing techniques. The ISR has become a popular research topic in the field of brain-computer interface (BCI), offering a promising solution to improve the quality of life for individuals with disabilities. Some innovative works have been published in recent years, however, there is a lack of reviews to give general readers a clear picture of ISR advances. To this end, our article comprehensively summarizes the recently published ISR-related works. The data acquisition and preprocessing methods of the involved neural signals are included, and the ISR advances from these neural signals are further summarized. The included concepts, methods, datasets, and discussions, are expected to be beneficial for both the general reader and academic researchers in this field.