The grammar behind Utter Command

Human-Machine Grammar

Human-Machine Grammar is a system of words and rules designed to allow humans to communicate commands to computers. It takes into consideration that humans have an extensive natural language capacity that has evolved over millions of years and that we use seemingly without effort, while computers do not yet have the ability to understand the meaning of speech.

It also takes into consideration that while language seems easy for humans, different phrasings encompass a considerable span of cognitive effort. Human-Machine Grammar is designed to limit cognitive effort in order to free up as much of the brain as possible to concentrate on the task at hand.

Natural language allows for a wide, textured range of communications, but controlling a computer only requires a relatively small set of distinct commands. Human-Machine Grammar is a relatively succinct set of words that can be combined according to a concise set of grammar rules to communicate a small set of commands. The system is relatively easy for humans to learn, and computers can respond to the commands without having to decode natural language or be loaded down with large sets of synonymous commands. (for more details see Structured vs. Natural Language)

Human-Machine Grammar, like any language system in use, is an active, evolving set of words and rules. Redstart Systems founder Kimberly Patch began using speech recognition software and writing custom speech macros in 1994. Over time it became obvious that a formal grammar was needed. She has been developing these ideas since 1998; much of what she developed, including the logic underpinning the grammar, is covered in a series of talks.

We encourage people to use the HMG system when writing custom speech commands.

Read the rules.

Read the words.