Glossary

Search results

Acoustic Event Detection(also: Sound Event Detection, Audio Event Detection, Sound Event Classification)

The automated process of identifying and classifying specific sounds within an audio stream, such as recognizing a phone ringing, door knocking, fire alarm, or speech from continuous environmental audio. Acoustic event detection systems use machine learning trained on labeled…

Adaptive Multi-Rate Codec(also: AMR, AMR Codec, AMR-NB)

A family of audio codecs used in mobile telephony to encode voice for transmission. AMR-NB (narrowband) operates at 300-3,400 Hz with bit rates from 4.75-12.2 kbps, while AMR-WB (wideband, also called HD Voice) extends to 50-7,000 Hz at 6.6-23.85 kbps. AMR-WB is adopted by 3GPP…

Ambient Audio(also: Ambient Sound, Environmental Audio, Background Audio)

The background sound of an environment — voices, traffic, water, wind, music, birdsong — captured incidentally rather than as the main focus of a recording. In accessible photography and audiophotography tools, ambient audio is often recorded automatically in the seconds leading…

AsTeR(also: Audio System for Technical Readings)

An interactive computing system developed by T. V. Raman in his 1994 PhD thesis at Cornell University that converts LaTeX documents into navigable audio documents. AsTeR parses electronic documents into a tree structure that listeners can interactively browse, enabling…

Audio Description Script(also: AD Script, Video Description Script, Described Video Script)

An audio description script is the written text that forms the basis of an audio description track for video content. The script contains narration that describes visual elements — including actions, scene changes, character appearances, on-screen text, and other visual…

Audio Formatting(also: Audio Rendering)

The process of converting structured electronic documents into audio output that conveys not just textual content but also the logical structure and formatting of the original document. Audio formatting uses synthesizer parameters such as pitch, stereo positioning, speaking…

Audio Game(also: Audiogame, Audio-Based Game, Accessible Game)

A video game designed primarily or entirely around audio output rather than visual graphics, making it accessible to players who are blind or have visual impairments. Audio games use techniques such as 3D spatial audio, sound effects, text-to-speech, and musical cues to convey…

Audio Guide(also: Audio Tour, Audio Description Tour, Museum Audio Guide)

A portable or installed audio system that provides spoken descriptions, narratives, or contextual information about exhibits in a museum, gallery, or cultural venue. Audio guides range from traditional handheld devices with numbered stops to smartphone apps with…

Audio-to-Haptics Translation(also: Audio-haptic translation, Audio-to-vibration conversion)

A class of techniques that convert audio signals — either recordings of real-world interactions or AI-generated sounds — into vibrotactile patterns that can be rendered through actuators embedded in phones, tablets, wearables, or specialized haptic displays. Because the…

Auditory Icon(also: Audio Icon)

A non-speech sound used in a user interface that represents an object, action, or event by mimicking its real-world sound — for example, the sound of crumpling paper to indicate deleting a file, or a camera shutter sound for taking a screenshot. Auditory icons rely on causal…

10 results.