论文标题
自适应的几种学习算法，用于罕见的声音事件检测
Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection
论文作者
论文摘要
声音事件检测是通过了解周围的环境声音来推断事件。由于罕见的声音事件的稀缺性，对于训练有素的探测器而言，它变得具有挑战性，这些探测器学会了太多的先验知识。同时，在面对新的有限数据任务时，很少有射击学习方法有望具有良好的概括能力。最近的方法在这一领域取得了令人鼓舞的结果。但是，这些方法独立对待每个支持示例，忽略了整个任务中其他示例的信息。因此，大多数以前的方法都受到约束，以生成对所有测试时间任务的相同功能嵌入，这并不适合每个输入的数据。在这项工作中，我们提出了一个新型的任务自适应模块，该模块易于种植到任何基于指标的少量学习框架中。该模块可以识别与任务相关的特征维度。合并我们的模块可以在两个数据集上大大提高基线方法的性能，尤其是对于偏置繁殖网络。例如，ESC-50的5路1-shot精度为 +6.8％，noiseESC-50的 +5.9％。我们研究了在域 - 匹配设置中的方法，并且比以前的方法获得了更好的结果。
Sound event detection is to infer the event by understanding the surrounding environmental sounds. Due to the scarcity of rare sound events, it becomes challenging for the well-trained detectors which have learned too much prior knowledge. Meanwhile, few-shot learning methods promise a good generalization ability when facing a new limited-data task. Recent approaches have achieved promising results in this field. However, these approaches treat each support example independently, ignoring the information of other examples from the whole task. Because of this, most of previous methods are constrained to generate a same feature embedding for all test-time tasks, which is not adaptive to each inputted data. In this work, we propose a novel task-adaptive module which is easy to plant into any metric-based few-shot learning frameworks. The module could identify the task-relevant feature dimension. Incorporating our module improves the performance considerably on two datasets over baseline methods, especially for the transductive propagation network. Such as +6.8% for 5-way 1-shot accuracy on ESC-50, and +5.9% on noiseESC-50. We investigate our approach in the domain-mismatch setting and also achieve better results than previous methods.
