Glossary

Searchable terminology from accessibility, web standards, and related fields.

40 results found in Captioning.

Affective Captions (Affective Captioning, Emotive Captions)
Captions that convey not only the spoken words but also the emotional qualities of speech — such as valence (positive vs. negative tone) and arousal (intensity) — typically through typographic modulat…
Automated Speech Recognition (ASR, Speech-to-Text, Voice Recognition)
Technology that converts spoken language into written text using machine learning and signal processing algorithms. In accessibility, ASR is used for real-time captioning, voice control of devices and…
Automatic Caption Evaluation (ACE, ACE Framework, ACE Metric)
A caption-quality evaluation framework introduced by Sushant Kafle and Matt Huenerfauth (2017-2018) that scores automatically generated captions based on their usability for Deaf and Hard-of-Hearing r…
Automatic Captions (Auto-Generated Captions, Auto Captions, ASR Captions)
Captions produced by automatic speech recognition (ASR) systems without human transcription, typically generated by the hosting platform (e.g., YouTube, Zoom, Microsoft Teams) as an optional layer on …
C-Print (C-Print Pro)
A meaning-for-meaning real-time captioning service where a trained captioner produces a condensed transcription of spoken classroom content, as opposed to the verbatim word-for-word transcription prov…
CART (Communication Access Realtime Translation, Computer-Aided Real-Time Translation)
A real-time captioning service in which a trained stenographer uses a specialized keyboard to transcribe spoken language into text as it is spoken, typically achieving accuracy rates above 98%. CART i…
CART (Communication Access Realtime Translation, Real-Time Captioning, Realtime Captioning)
A professional service providing instant, verbatim text display of spoken content, typically delivered by trained stenographers using specialized equipment. CART achieves accuracy rates of 98% or high…
CART (Communication Access Real-Time Translation, Real-Time Captioning, Stenography, Real-Time Stenography)
A real-time captioning service where a trained stenographer uses a specialized keyboard to transcribe speech into text as it is spoken, typically with only a few seconds of delay. CART provides word-f…
CEA-708 (CTA-708, EIA-708, Digital Closed Captioning)
A US standard for digital closed captioning on digital television broadcasts and streaming, superseding the analog-era CEA-608 standard. CEA-708 supports richer presentation than its predecessor, incl…
Caption Accuracy (Captioning Accuracy, Transcription Accuracy)
A measure of how correctly captions represent the spoken content, typically expressed as the percentage of words that match the ground truth transcript. Caption accuracy is critical for deaf and hard …
Caption Flow (Captioning Flow, Text Flow)
The smoothness and regularity with which caption text appears and updates on screen during real-time captioning. Good caption flow means text arrives at a consistent pace without jarring delays, sudde…
Caption Quality (Subtitle Quality)
The overall fitness of a set of captions or subtitles for their intended accessibility purpose. Quality is multi-dimensional: it includes text accuracy (whether spoken words are correctly transcribed,…
Communication Access Realtime Translation (CART, Realtime Captioning, Stenographic Captioning)
A captioning service where a trained professional uses a stenographic keyboard to transcribe spoken language into text in real time, producing near-verbatim captions. CART provides the highest accurac…
Hybrid Captioning (AI-Augmented Captioning, Blended Captioning)
A captioning approach that combines human-generated captions with AI-powered correction or enhancement to achieve higher accuracy than either method alone. Hybrid systems leverage the reliability and …
Keyword Reading Strategy (Content Word Strategy)
The keyword reading strategy is a sentence-comprehension approach in which a reader focuses primarily on high-content words (nouns, verbs, adjectives, and adverbs) to derive the meaning of a sentence,…
Latency (Delay, Lag, Response Time)
The time delay between when an event occurs and when its accessible representation is delivered to the user. In real-time captioning, latency is the gap between spoken words and their appearance as te…
NER Model (Number, Edition, Recognition Model, NER Accuracy Model)
A caption-quality evaluation model developed by Pablo Romero-Fresco and Juan Martínez Pérez for measuring the accuracy of live subtitling and respeaking. Unlike Word Error Rate, which penalises all er…
Participatory Captioning
A framework proposed by Nguyen et al. (2026) that characterises social media video captioning as a collaborative, community-sustained infrastructure co-produced by viewers, creators, and platforms — r…
Re-speaking (Respeaking, Speech-to-Text Relay)
A captioning technique in which a trained operator listens to a speaker and repeats (re-speaks) their words clearly into a high-quality microphone in a controlled environment, allowing automatic speec…
Real-Time Captioning (CART, Communication Access Realtime Translation, Live Captioning, Real-Time Text)
The instant conversion of spoken language into text displayed simultaneously as speech occurs, provided either by a trained human captioner or through automatic speech recognition (ASR) technology. Re…