GISE-51：可扩展的孤立声音事件数据集
GISE-51: A scalable isolated sound events dataset
摘要：
大多数现有的孤立的声音事件数据集包括少量的声音事件类别，通常为10至15个，限于一个小的领域，如家庭和城市的声音事件。在这项工作中，我们介绍了GISE-51，一个数据集跨越51个孤立的声音事件属于一个广泛的域的事件类型。我们还发布了GISE-51-Mixtures，这是一个5秒音景数据集，具有从GISE-51孤立声音事件合成的硬标记事件边界。我们在GISE-51-Mixtures数据集上进行了基线声音事件识别（SER）实验，对著名的卷积神经网络进行了基准测试，使用该数据集训练的模型在现有的音频识别基准测试中表现出强大的迁移学习性能。GISE-51和GISE-51-Mixtures一起试图解决最近声音事件数据集的一些缺点，为未来的研究提供一个开放的，可重复的基准，以及为特定领域的应用程序调整所包含的孤立声音事件的自由。
英文摘要：
Most of the existing isolated sound event datasets comprise a small number of sound event classes, usually 10 to 15, restricted to a small domain, such as domestic and urban sound events. In this work, we introduce GISE-51, a dataset spanning 51 isolated sound events belonging to a broad domain of event types. We also release GISE-51-Mixtures, a dataset of 5-second soundscapes with hard-labelled event boundaries synthesized from GISE-51 isolated sound events. We conduct baseline sound event recognition (SER) experiments on the GISE-51-Mixtures dataset, benchmarking prominent convolutional neural networks, and models trained with the dataset demonstrate strong transfer learning performance on existing audio recognition benchmarks. Together, GISE-51 and GISE-51-Mixtures attempt to address some of the shortcomings of recent sound event datasets, providing an open, reproducible benchmark for future research along with the freedom to adapt the included isolated sound events for domain-specific applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
