Real-Time Captioning

The process of converting spoken language to text simultaneously or with minimal delay as the speech occurs. Real-time captioning can be produced by human transcriptionists (CART, C-Print, TypeWell), crowd workers, automatic speech recognition (ASR), or hybrid approaches. Unlike pre-recorded captions, real-time captions must be generated on-the-fly, which presents unique challenges including transcription delay (typically 2-5 seconds), variable accuracy, lack of prosody information, and unformatted text that constantly changes. Research shows that reading real-time captions requires more cognitive effort than reading static text, and the most comfortable reading rate for deaf viewers is around 145 words per minute compared to 280-300 wpm for print.