人类与ASR生成的非洲裔美国人英语转录文本的风格差异量化
Quantification of stylistic differences in human- and ASR-produced transcripts of African American English
AI总结：
本文通过分类10小时非洲裔美国人英语语音的6个转录版本中的风格差异，研究逐字特征和形态句法特征对词错误率评估的影响，揭示ASR输出受训练数据中人类转录决策制约的机制。
摘要：
用于评估自动语音识别（ASR）系统以及人类转录员表现的常用准确率指标混淆了多种错误来源。当训练数据集与测试数据集之间存在差异时，风格差异（例如逐字转录与非逐字转录）会对ASR性能评估产生显著影响。对于代表性不足的语言变体而言，这一问题更加严重，因为其语音到正字法的映射尚未充分标准化。我们对10小时非洲裔美国人英语（AAE）语音的6个转录版本（4个人工转录版本和2个ASR生成版本）之间的风格差异类型进行了分类。我们重点关注逐字转录特征和AAE形态句法特征，研究了这些类别与通过词错误率（WER）比较转录文本质量之间的相互作用。实验结果和整体分析有助于阐明ASR输出如何取决于训练数据中人类转录员所做的决策。
英文摘要：
Common measures of accuracy used to assess the performance of automatic speech recognition (ASR) systems, as well as human transcribers, conflate multiple sources of error. Stylistic differences, such as verbatim vs non-verbatim, can play a significant role in ASR performance evaluation when differences exist between training and test datasets. The problem is compounded for speech from underrepresented varieties, where the speech to orthography mapping is not as standardized. We categorize the kinds of stylistic differences between 6 transcription versions, 4 human- and 2 ASR-produced, of 10 hours of African American English (AAE) speech. Focusing on verbatim features and AAE morphosyntactic features, we investigate the interactions of these categories with how well transcripts can be compared via word error rate (WER). The results, and overall analysis, help clarify how ASR outputs are a function of the decisions made by the training data's human transcribers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
