Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER
Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats every lexical deviation from the reference as equally costly, regardless of whether it changes meaning. This raises the question: does WER actually track how humans judge ASR transcript quality? We introduce HATS-en, an...
Hritika Sharma, Thibault Bañeras-Roux, Alessandra Pinto et al.
· 0 citations