Glossary
Terms used in accessibility research and practice. Each entry has a definition, common aliases, and category tags.
Search results
- Wav2Vec(also: Wav2Vec2, Wav2Vec 2.0)
- A family of self-supervised speech representation models from Meta AI that learn rich acoustic embeddings directly from raw waveform audio without requiring transcribed training data. Wav2Vec 2.0, introduced in 2020, became a backbone for low-resource automatic speech…
- WebVTT(also: Web Video Text Tracks, Web Video Text Tracks Format)
- WebVTT (Web Video Text Tracks) is the W3C standard text format for providing timed text tracks — including captions, subtitles, descriptions, chapters, and metadata — synchronized with HTML5 <video> and <audio> elements. WebVTT evolved from the earlier SRT subtitle format,…
- Word Error Rate(also: WER)
- A standard metric for evaluating speech recognition and captioning accuracy, calculated as the number of insertions, deletions, and substitutions needed to transform the transcribed text into the reference text, divided by the total number of words in the reference. Lower WER…
- Word Error Rate(also: WER)
- A metric used to evaluate the accuracy of automatic speech recognition (ASR) and captioning systems, calculated as the number of word-level errors (insertions, deletions, and substitutions) divided by the total number of words in the reference transcript. Lower WER indicates…
4 results.