Agmon Galit, Pradhan Sameer, Ash Sharon, Nevler Naomi, Liberman Mark, Grossman Murray, Cho Sunghye
Frontotemporal Degeneration Center, Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia.
Linguistic Data Consortium, University of Pennsylvania, Philadelphia.
J Speech Lang Hear Res. 2024 Feb 12;67(2):545-561. doi: 10.1044/2023_JSLHR-23-00009. Epub 2024 Jan 12.
Multiple methods have been suggested for quantifying syntactic complexity in speech. We compared eight automated syntactic complexity metrics to determine which best captured verified syntactic differences between old and young adults.
We used natural speech samples produced in a picture description task by younger ( = 76, ages 18-22 years) and older ( = 36, ages 53-89 years) healthy participants, manually transcribed and segmented into sentences. We manually verified that older participants produced fewer complex structures. We developed a metric of syntactic complexity using automatically extracted syntactic structures as features in a multidimensional metric. We compared our metric to seven other metrics: Yngve score, Frazier score, Frazier-Roark score, developmental level, syntactic frequency, mean dependency distance, and sentence length. We examined the success of each metric in identifying the age group using logistic regression models. We repeated the analysis with automatic transcription and segmentation using an automatic speech recognition (ASR) system.
Our multidimensional metric was successful in predicting age group (area under the curve [AUC] = 0.87), and it performed better than the other metrics. High AUCs were also achieved by the Yngve score (0.84) and sentence length (0.84). However, in a fully automated pipeline with ASR, the performance of these two metrics dropped (to 0.73 and 0.46, respectively), while the performance of the multidimensional metric remained relatively high (0.81).
Syntactic complexity in spontaneous speech can be quantified by directly assessing syntactic structures and considering them in a multivariable manner. It can be derived automatically, saving considerable time and effort compared to manually analyzing large-scale corpora, while maintaining high face validity and robustness.
已提出多种用于量化言语中句法复杂性的方法。我们比较了八种自动句法复杂性指标，以确定哪种指标能最好地捕捉老年人和年轻人之间已证实的句法差异。
我们使用了由年轻（(n = 76)，年龄在18 - 22岁）和年长（(n = 36)，年龄在53 - 89岁）健康参与者在图片描述任务中生成的自然言语样本，进行人工转录并分割成句子。我们人工验证了年长参与者生成的复杂结构较少。我们开发了一种句法复杂性指标，使用自动提取的句法结构作为多维度指标中的特征。我们将我们的指标与其他七个指标进行比较：英格夫分数、弗雷泽分数、弗雷泽 - 罗克分数、发展水平、句法频率、平均依存距离和句子长度。我们使用逻辑回归模型检验了每个指标在识别年龄组方面的成功率。我们使用自动语音识别（ASR）系统进行自动转录和分割后重复了该分析。
我们的多维度指标成功预测了年龄组（曲线下面积[AUC] = 0.87），并且其表现优于其他指标。英格夫分数（0.84）和句子长度（0.84）也获得了较高的AUC值。然而，在使用ASR的全自动流程中，这两个指标的表现下降（分别降至0.73和0.46），而多维度指标的表现仍相对较高（0.81）。
自发言语中的句法复杂性可以通过直接评估句法结构并以多变量方式考虑它们来量化。它可以自动得出，与人工分析大规模语料库相比节省了大量时间和精力，同时保持较高的表面效度和稳健性。
