Deep learning methods have achieved high performance in sound recognition tasks. Deciding how to feed the training data is important for further performance improvement. We propose a novel learning method for deep sound recognition: Between-Class learning (BC learning). Our strategy is to learn a discriminative feature space by recognizing the between-class sounds as between-class sounds. We generate between-class sounds by mixing two sounds belonging to different classes with a random ratio. We then input the mixed sound to the model and train the model to output the mixing ratio. The advantages of BC learning are not limited only to the increase in variation of the training data; BC learning leads to an enlargement of Fisher's criterion in the feature space and a regularization of the positional relationship among the feature distributions of the classes. The experimental results show that BC learning improves the performance on various sound recognition networks, datasets, and data augmentation schemes, in which BC learning proves to be always beneficial. Furthermore, we construct a new deep sound recognition network (EnvNet-v2) and train it with BC learning. As a result, we achieved a performance surpasses the human level.

该研究提出了一种名为 BC learning 的新型深度学习方法，通过识别类间声音来学习区分性特征空间，该方法不仅仅可以增加训练数据的多样性，还可以增加 Fisher 的判据，规范类之间特征分布的关系。该方法可以在各种声音识别网络、数据集和数据增强方案中提高性能，并通过构建深度声音识别网络 EnvNet-v2 并使用 BC learning 方法，实现了超越人类的性能。

利用类间样本进行深度声音识别学习