论文标题
用于声音事件检测的增量学习算法
Incremental Learning Algorithm for Sound Event Detection
论文作者
论文摘要
本文提出了一种新的学习策略（SED检测），以解决i）i）知识从预训练的模型到新目标模型以及ii）学习新的声音事件而不忘记以前学习的事件而不重新训练的新声音事件。为了将先前学到的知识从源模型迁移到目标，在源模型的顶部采用了神经适配器。源模型和目标模型通过此神经适配器层合并。神经适配器层促进了目标模型，以最少的训练数据学习新的声音事件，并维持与源模型相似的先前学习的声音事件的性能。我们对DCASE16和US-SED数据集的广泛分析揭示了该方法在源模型和目标模型之间转移知识的有效性，而无需在以前学习的声音事件上引入任何性能降低，同时在新学习的声音事件上获得了竞争性检测性能。
This paper presents a new learning strategy for the Sound Event Detection (SED) system to tackle the issues of i) knowledge migration from a pre-trained model to a new target model and ii) learning new sound events without forgetting the previously learned ones without re-training from scratch. In order to migrate the previously learned knowledge from the source model to the target one, a neural adapter is employed on the top of the source model. The source model and the target model are merged via this neural adapter layer. The neural adapter layer facilitates the target model to learn new sound events with minimal training data and maintaining the performance of the previously learned sound events similar to the source model. Our extensive analysis on the DCASE16 and US-SED dataset reveals the effectiveness of the proposed method in transferring knowledge between source and target models without introducing any performance degradation on the previously learned sound events while obtaining a competitive detection performance on the newly learned sound events.
