Lahiri Rimita, Nasir Md, Kumar Manoj, Kim So Hyun, Bishop Somer, Lord Catherine, Narayanan Shrikanth
Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, California 90089, USA.
Microsoft Artificial Intelligence for Good Research Lab, Redmond, Washington 98052, USA.
JASA Express Lett. 2022 Sep;2(9):095202. doi: 10.1121/10.0013421. Epub 2022 Sep 8.
Quantifying behavioral synchrony can inform clinical diagnosis, long-term monitoring, and individualised interventions in neuro-developmental disorders characterized by deficit in communication and social interaction, such as autism spectrum disorder. In this work, three different objective measures of interpersonal synchrony are evaluated across vocal and linguistic communication modalities. For vocal prosodic and spectral features, dynamic time warping distance and squared cosine distance of (feature-wise) complexity are used, and for lexical features, word mover's distance is applied to capture behavioral synchrony. It is shown that these interpersonal vocal and linguistic synchrony measures capture complementary information that helps in characterizing overall behavioral patterns.
量化行为同步性可为临床诊断、长期监测以及针对以沟通和社交互动缺陷为特征的神经发育障碍（如自闭症谱系障碍）的个性化干预提供依据。在这项研究中，我们评估了三种不同的人际同步性客观测量方法，涵盖了语音和语言交流方式。对于语音韵律和频谱特征，使用动态时间规整距离和（逐特征）复杂度的平方余弦距离；对于词汇特征，则应用词移距离来捕捉行为同步性。结果表明，这些人际语音和语言同步性测量方法捕捉到了互补信息，有助于刻画整体行为模式。
