Glossary

Search results

Speech Repair(also: Self-Correction, Speech Self-Repair, Command Correction)

Speech repair is the process of correcting or modifying a spoken utterance after it has been produced, either within the same turn or in a subsequent one. In natural conversation, speakers commonly interrupt themselves to fix errors, change wording, or update information using…

Speech-Based Cursor Control(also: Voice Cursor Control, Speech-Driven Pointing)

A method of controlling a computer's pointing cursor using spoken voice commands rather than a mouse, trackpad, or other physical pointing device. Users speak directional commands (such as "move left," "move up") to start cursor movement and a stop command to halt it, then issue…

Speech-Based Cursor Movement(also: Voice-Controlled Cursor, Voice Cursor Control)

A technique for moving the on-screen cursor using voice commands rather than physical manipulation of a pointing device. Speech-based cursor movement systems typically use one of two approaches: discrete specification, where the user speaks a command to jump the cursor to a…

Spoken Dialog System(also: SDS, Voice Dialog System, Conversational AI)

A computer system that uses speech as both input and output to conduct goal-oriented conversations with users. Unlike simple voice command systems, spoken dialog systems can handle multi-turn exchanges, track conversation context, manage misunderstandings, and adapt to user…

Spoken Dialogue System(also: SDS, Voice Dialogue System)

A computer system that communicates with users through spoken natural language, allowing them to interact via voice rather than visual or manual interfaces. Spoken dialogue systems are used in telecare, customer service, and home care applications, and are particularly relevant…

Spoken Web(also: World Wide Telecom Web, WWTW, Telecom Web)

An alternative web paradigm designed for people in developing regions who are excluded from the traditional World Wide Web by illiteracy, unaffordability, or lack of locally relevant content. In the Spoken Web, nodes are voice applications called VoiceSites that are created by…

Subvocal Input(also: Subvocal Control, Subvocalisation Input)

An input method that uses very quiet or nearly silent vocalisations — sounds produced with minimal vocal effort that are typically inaudible to nearby people. Subvocal input includes techniques such as humming, whispering, or producing sounds detectable only by bone-conduction…

7 results.