Designing Effective Speech Interfaces

What Is a Speech Interface?

It seems as if this question, What is a Speech Interface?, would be simple to answer, but it is not. Because it is a relatively new idea to have our technology involve speech, this is a field that is just starting to grow. Like any new field, the definitions and terminologies are not standard. Here are some of the current terms in use, what they usually mean, and how we will apply them here.

Speech Interfaces

The term speech interface describes a software interface that employs either human speech or simulated human speech. You can further break down speech interfaces into auditory user interfaces and graphical user interfaces with speech.

Auditory User Interfaces (AUI)

An auditory user interface (AUI) is an interface which relies primarily or exclusively on audio for interaction, including speech and sounds. This means that commands issued by the machine or computer, as well as all commands issued by the human to control the machine or computer, are executed primarily with speech and sounds. Although AUI may include a hardware component, such as a keypad or buttons, visual displays are not used for critical information. Examples of auditory user interfaces include

• medical transcription software that allows doctors to dictate medical notes while making rounds;
• automobile hands-free systems that allow drivers to access travel information and directions (systems without screens and maps);
• interactive voice response (IVR) systems in which users access ...