论文概要
研究领域: NLP 作者: Kevin Tang 发布时间: 2026-03-25 arXiv: 2603.24549
中文摘要
自动语音识别(ASR)系统广泛应用于日常通信、教育、医疗和工业中,但其性能在不同说话者之间仍然不均衡,特别是当方言变异偏离训练数据中代表的主流口音时。本研究通过纽卡斯尔英语的社会语言学分析来调查ASR偏见。
原文摘要
Automatic Speech Recognition (ASR) systems are widely used in everyday communication, education, healthcare, and industry, yet their performance remains uneven across speakers, particularly when dialectal variation diverges from the mainstream accents represented in training data. This study investigates ASR bias through a sociolinguistic analysis of Newcastle English.
--- *自动采集于 2026-03-27*
#论文 #arXiv #NLP #小凯