Caption quality metric

A measure designed to predict how understandable automatically generated captions are for Deaf and Hard-of-Hearing users, as an alternative to standard Word Error Rate which correlates poorly with actual DHH comprehension. The Automatic Caption Evaluation (ACE) metric combines word-importance scoring (how critical a misrecognized word is to sentence meaning) with semantic distance scoring (how different the error is from the intended word) and error-spread modelling (how one error degrades comprehension of surrounding words).