Voice user interface

A voice user interface lets people interact with a device or service by speaking commands or questions, often through speech recognition and spoken responses.

Automatic speech recognition: Technology that converts spoken audio into written words or other representations of speech. It transforms spoken input into a form the interface can interpret.
Speech signal: An acoustic waveform produced by human speech, carrying linguistic and speaker information. The interface receives speech as sound before processing its words.
Virtual assistant: Software that performs tasks or answers questions through conversational interaction. Many virtual assistants use speech as their main input and output mode.
Graphical user interface: An interface that uses visual elements such as windows, icons, and menus for interaction. Unlike voice, it presents visible controls and supports visual scanning.
Natural language understanding: Computational methods for identifying meaning, intent, and entities in human language. It helps determine what a spoken request asks the system to do.
Phonetics: The study of speech sounds, including their production, acoustic properties, and perception. Sound distinctions shape how spoken input can be recognized.
Interactive voice response: A telephone system that routes calls or provides information through spoken prompts and user responses. It applies voice interaction to automated telephone services.
Touchscreen: A display that detects touch input to control a device or application. Touch offers direct physical selection where spoken commands may be ambiguous.
Wake word: A word or phrase that activates a voice-controlled device or listening mode. It lets an interface begin attending to speech without continuous manual activation.
Pragmatics: The study of how context influences the meaning of language in use. A request's intended meaning can differ from its literal wording.

Linked from 12 pages