INFANT CRYING DETECTION IN REAL-WORLD ENVIRONMENTS.
INFANT CRYING DETECTION IN REAL-WORLD ENVIRONMENTS.
复制标题
现实环境中的婴儿哭泣检测。
DOI：
10.1109/icassp43922.2022.9746096
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
deBarbaro,Kaya
中科院分区：
文献类型：
--
作者：
Yao,Xuewen;Micheletti,Megan;Johnson,Mckensey;Thomaz,Edison;deBarbaro,Kaya
大多数现有的哭泣检测模型已经在受控环境中收集的数据进行了测试。因此，他们在多大程度上推广到嘈杂和生活的环境是不清楚的。在本文中，我们评估了几种已建立的机器学习方法，包括利用深谱和声学特征的模型。该模型能够识别哭泣事件，F1得分为0.613（精确度：0.672，召回率：0.552），在日常现实世界环境中，与现有的哭泣检测方法相比，外部有效性有所提高。作为评估的一部分，我们收集并注释了一个新的婴儿哭声数据集，该数据集是从超过780小时的标记真实世界音频数据中汇编而成的，这些数据是通过婴儿在家中佩戴的录音机捕获的，我们将其公开提供。我们的研究结果证实，在实验室数据上训练的哭泣检测模型在现实世界的数据中表现不佳（实验室测试F1：0.656，现实世界测试F1：0.236），突出了我们新数据集和模型的价值。
Most existing cry detection models have been tested with data collected in controlled settings. Thus, the extent to which they generalize to noisy and lived environments is unclear. In this paper, we evaluate several established machine learning approaches including a model leveraging both deep spectrum and acoustic features. This model was able to recognize crying events with F1 score 0.613 (Precision: 0.672, Recall: 0.552), showing improved external validity over existing methods at cry detection in everyday real-world settings. As part of our evaluation, we collect and annotate a novel dataset of infant crying compiled from over 780 hours of labeled real-world audio data, captured via recorders worn by infants in their homes, which we make publicly available. Our findings confirm that a cry detection model trained on in-lab data underperforms when presented with real-world data (in-lab test F1: 0.656, real-world test F1: 0.236), highlighting the value of our new dataset and model.