A Voice User Interface (VUI) is a human-computer interaction modality in which users issue commands and receive responses through spoken language rather than visual controls. It chains automatic speech recognition, natural-language understanding, dialogue management and speech synthesis to turn utterances into actions and synthesised replies. VUIs power virtual assistants, in-car systems and accessibility tools where hands-free or eyes-free operation is valuable.
Overview
- User Interface provides the broader context within which Voice User Interface sits.
- Voice User Interface is treated here as a member of the artificial-intelligence domain at established maturity.
- It is referenced across the knowledge graph by classes that depend on or compose it, making it a central node that warranted an explicit definition.
Key aspects
- It comprises Speech Recognition.
- It comprises Speech Synthesis.
- It comprises Intent Classification.
- It comprises Dialogue System.
- It requires Automatic Speech Recognition.
- It requires Natural Language Understanding.
- It requires Text-to-Speech.
- It makes use of Natural Language Processing.
Mechanisms
- Voice User Interface operates by combining its constituent parts into a coherent capability that other classes can rely upon.
- Its guarantees and behaviours are realised through the dependencies and standards captured in the relations below.
Applications
- Enables and supports Conversational AI.
- Enables and supports Voice Assistant.
- Enables and supports Human-Computer Interaction.
- Enables and supports Accessibility.