Audio Engineering & Subtitle Terminology Directory

Peer-reviewed glossary of acoustic signal processing, automated speech recognition (ASR), closed captioning, and accessibility compliance terms.

Featured Technical Definitions

Word Error Rate (WER)

The standard mathematical metric for speech recognition accuracy: WER = (Substitutions + Deletions + Insertions) / Total Reference Words. Lower values denote superior transcription fidelity.

Diarization Error Rate (DER)

Measures the fraction of time that speaker identity is misattributed in multi-speaker audio recordings, evaluating missed speech, false alarms, and speaker confusion.

Nyquist-Shannon Sampling Theorem

Dictates that a digital audio recording must be sampled at at least twice the highest frequency component (f_s >= 2 * f_max) to prevent acoustic aliasing.

Characters Per Second (CPS)

The universal reading speed metric for subtitles and closed captions, typically restricted to 17-20 CPS to prevent cognitive visual overload.

CEA-608 & CEA-708

The United States standards for Line 21 analog and ATSC digital television closed captioning mandated under FCC 47 CFR § 79.1 regulations.