分析纽卡斯尔方言对语音识别的影响，揭示系统偏见来源
Automatic Speech Recognition Biases in Newcastle English: an Error Analysis
- 通过人工分析错误样本，定位方言导致的音、词、语法错误
- 发现识别'you'和'wor'等方言代词时错误率显著升高
- 建议增加方言数据多样性，适合关注语音识别公平性的研究者
自动语音识别（ASR）系统因训练数据偏向主流语种而难以处理地区方言。尽管已有研究揭示了种族、年龄和性别方面的偏差，但地区性偏差仍缺乏深入探讨。本研究聚焦于以发音复杂著称的新城英语，开展两阶段分析：首先对子样本进行人工错误分析，识别出导致识别错误的关键音韵、词汇及形态句法问题；其次重点分析 ASR 对方言代词 'yous' 和 'wor' 的系统性识别表现。结果显示，错误与地区方言特征直接相关，社会因素影响较小。研究呼吁提升 ASR 训练数据中的方言多样性，并强调社会语言学分析在诊断和缓解地区偏见中的价值。
原文摘要 · Abstract (English)
Automatic Speech Recognition (ASR) systems struggle with regional dialects due to biased training which favours mainstream varieties. While previous research has identified racial, age, and gender biases in ASR, regional bias remains underexamined. This study investigates ASR performance on Newcastle English, a well-documented regional dialect known to be challenging for ASR. A two-stage analysis was conducted: first, a manual error analysis on a subsample identified key phonological, lexical, and morphosyntactic errors behind ASR misrecognitions; second, a case study focused on the systematic analysis of ASR recognition of the regional pronouns ``yous'' and ``wor''. Results show that ASR errors directly correlate with regional dialectal features, while social factors play a lesser role in ASR mismatches. We advocate for greater dialectal diversity in ASR training data and highlight the value of sociolinguistic analysis in diagnosing and addressing regional biases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。