Kendall Tyler, Vaughn Charlotte, Farrington Charlie, Gunter Kaylynn, McLean Jaidan, Tacata Chloe, Arnson Shelby
Linguistics Department, University of Oregon, Eugene, OR, United States.
Language Science Center, University of Maryland, College Park, MD, United States.
Front Artif Intell. 2021 Apr 29;4:648543. doi: 10.3389/frai.2021.648543. eCollection 2021.
Impressionistic coding of sociolinguistic variables like English (ING), the alternation between pronunciations like and , has been a central part of the analytic workflow in studies of language variation and change for over a half-century. Techniques for automating the measurement and coding for a wide range of sociolinguistic data have been on the rise over recent decades but procedures for coding some features, especially those without clearly defined acoustic correlates like (ING), have lagged behind others, such as vowels and sibilants. This paper explores computational methods for automatically coding variable (ING) in speech recordings, examining the use of automatic speech recognition procedures related to forced alignment (using the Montreal Forced Aligner) as well as supervised machine learning algorithms (linear and radial support vector machines, and random forests). Considering the automated coding of pronunciation variables like (ING) raises broader questions for sociolinguistic methods, such as how much different human analysts agree in their impressionistic codes for such variables and what data might act as the "gold standard" for training and testing of automated procedures. This paper explores several of these considerations in automated, and manual, coding of sociolinguistic variables and provides baseline performance data for automated and manual coding methods. We consider multiple ways of assessing algorithms' performance, including agreement with human coders, as well as the impact on the outcome of an analysis of (ING) that includes linguistic and social factors. Our results show promise for automated coding methods but also highlight that variability in results should be expected even with careful human coded data. All data for our study come from the public Corpus of Regional African American Language and code and derivative datasets (including our hand-coded data) are available with the paper.
对社会语言变量（如英语中的（ING），即 和 发音之间的交替）进行印象式编码，在半个多世纪以来一直是语言变异与变化研究分析流程的核心部分。近几十年来，用于自动测量和编码各种社会语言数据的技术不断涌现，但对某些特征（尤其是那些没有明确声学关联的特征，如（ING））的编码程序却落后于其他特征，如元音和咝音。本文探讨了在语音记录中自动编码变量（ING）的计算方法，研究了与强制对齐相关的自动语音识别程序（使用蒙特利尔强制对齐器）以及监督机器学习算法（线性和径向支持向量机，以及随机森林）的使用情况。考虑到像（ING）这样的发音变量的自动编码，会引发关于社会语言方法的更广泛问题，比如不同的人工分析员对这类变量的印象式编码的一致程度如何，以及哪些数据可作为自动程序训练和测试的 “黄金标准”。本文探讨了在社会语言变量的自动和手动编码中涉及的其中一些考量因素，并提供了自动和手动编码方法的基线性能数据。我们考虑了评估算法性能的多种方法，包括与人工编码员的一致性，以及对包含语言和社会因素的（ING）分析结果的影响。我们的结果显示了自动编码方法的前景，但也突出表明，即使是经过仔细人工编码的数据结果也会存在变异性。我们研究的所有数据均来自公开的《非裔美国地区语言语料库》，本文还提供了代码及衍生数据集（包括我们的人工编码数据）。
