English(EN) HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics

新HATS数据集整合人类感知用于ASR评估

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-30 07:48

研究人员推出HATS，一个新设计的法语数据集，旨在通过整合人类感知来评估自动语音识别（ASR）系统。该数据集是通过让143人比较并选择由不同ASR系统生成的两个转录选项中的更好一个来创建的。此举旨在超越传统的词错误率（WER）等指标，这些指标被认为不足以从人类用户的角度评估ASR质量。 AI

影响引入了一个用于评估ASR系统的新数据集，可能导致更符合人类的转录质量评估。

排序理由该集群描述了一篇介绍用于ASR评估的新型数据集的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Thibault Ba\~neras Roux, Jane Wottawa, Mickael Rouvier, Teva Merlin, Richard Dufour · 2026-05-01 04:00

HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics

arXiv:2604.27542v1 Announce Type: new Abstract: Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for evaluati…
arXiv cs.CL TIER_1 English(EN) · Richard Dufour · 2026-04-30 07:48

HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics

Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for evaluating speech transcripts. Several studies have show…