Abstract
Analyzing ultrasonic vocalizations (USVs) is crucial for understanding rodents' affective states and social behaviors, but the manual analysis is time-consuming and prone to errors. Automated USV detection systems have been developed to address these challenges. Yet, these systems often rely on machine learning and fail to generalize effectively to new datasets. To tackle these shortcomings, we introduce ContourUSV, an efficient automated system for detecting USVs from audio recordings. Our pipeline includes spectrogram generation, cleaning, pre-processing, contour detection, post-processing, and evaluation against manual annotations. To ensure robustness and reliability, we compared ContourUSV with three state-of-the-art systems using an existing open-access USV dataset (USVSEG) and a second dataset we are releasing publicly along with this paper. On average, across the two datasets, ContourUSV outperformed the other three systems with a 1.51x improvement in precision, 1.17x in recall, 1.80x in F1 score, and 1.49x in specificity while achieving an average speedup of 117.07x.
Abstract (translated)
分析超声波发声（USVs）对于理解啮齿动物的情感状态和社会行为至关重要，但手动分析耗时且容易出错。为了解决这些问题，开发了自动化USV检测系统。然而，这些系统通常依赖于机器学习，并且在面对新数据集时泛化效果不佳。为了克服这些缺点，我们介绍了ContourUSV，这是一个高效的自动化系统，用于从音频记录中检测USVs。我们的流程包括光谱图生成、清理、预处理、轮廓检测、后期处理和与手动注释的评估。为了确保稳健性和可靠性，我们将ContourUSV与三个最先进的系统进行了比较，使用了一个现有的开放访问USV数据集（USVSEG）以及我们在本文中同时发布的第二个公开数据集。在两个数据集上平均而言，ContourUSV在精度方面提高了1.51倍，在召回率方面提高了1.17倍，在F1分数方面提高了1.80倍，在特异性方面提高了1.49倍，并且实现了117.07倍的平均加速。
URL
https://arxiv.org/abs/2503.18928
