Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study

Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study 待解读

下载

可分享卡片

适合发到公众号、飞书、社群群发，帮助团队复用高质量解读。

Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study
作者: Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil, Sergio Burdisso, Petr Motlicek, Shiran Liu, Mickael Rouvier, Jane Wottawa, Richard Dufour

Automatic Speech Recognition (ASR) is typically evaluated using Word Error Rate (WER), which poorly reflects semantic similarity. While embedding-based metrics correlate better with human judgments, the respective roles…

详情页: https://ourxiv.cn/2608.25574v1

分享到 X

新用户看这篇论文该怎么开始

先点「赞助解读」，AI 会把论文转成可直接执行的行动清单。
看完“可执行改进行动”后，可快速决定是否值得立项。
用上面的卡片内容直接发给团队，减少重复阅读。

先订阅关键词，后续不再手工筛论文

摘要

Automatic Speech Recognition (ASR) is typically evaluated using Word Error Rate (WER), which poorly reflects semantic similarity. While embedding-based metrics correlate better with human judgments, the respective roles of encoder and decoder-based Large Language Models (LLMs) remain underexplored. This paper presents a comparative study of both families for ASR evaluation. We analyze BERTScore and SemDist across different LLMs, layers, and pooling strategies, showing that both metrics can achieve strong correlation with human judgments when properly configured. For decoder models, we investigate generative LLMs in two settings: pairwise hypothesis selection via prompting and direct qualitative error classification. Our results show that encoder-based metrics remain highly competitive, while generative LLMs perform strongly in hypothesis comparison and improve the interpretability of ASR evaluation.

分析报告

暂无报告。点击“分析”开始生成。

个性化解读与社区共享解读不同

用自己的话告诉 AI 你想要什么样的解读（比如"用大白话讲给非专业人士听"、"重点分析对我们团队 RAG 系统的可迁移性"），生成一份只属于你自己的版本；生成后也可以选择设为"愿意共享"，被更多人看到、点赞。