Evaluation of Automatic Speech Recognition Using Generative Large Language Models 事件

Evaluation of Automatic Speech Recognition Using Generative Large Language Models arXiv:2604.21928v3 Announce Type: replace Abstract: Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large Language Models (LLMs) remain underexplored for this task. This paper evaluates their relevance through three approaches: (1) selec