Introduction

Abstract

The concept of silent speech, when applied to human–computer interaction (HCI), describes a system that allows for speech communication between humans and machines in the absence of an audible acoustic signal. This type of system can be used as an input HCI modality in high-background-noise environments such as in living rooms, or in aiding speech-impaired individuals. The audible acoustic signal is, in fact, just the end result of the complex process of speech production, which starts at the brain, triggers relevant muscular activity, and results in movements of the articulators. It is this information that silent speech interfaces (SSIs) strive to harness and, in this context, understanding the different stages of speech production is of major importance. In this chapter, the reader finds a brief introduction into the historical context for the rising interest in silent speech, followed by an overview on the different stages involved in speech production. Along the way, we establish a correspondence between the natural speech production process and the technology, which will be further discussed in the following chapters, leading to the existing silent speech interface (SSI) systems. Additionally, we identify overall challenges in the development of SSI.