Learning from Between-class Examples for Deep Sound Recognition

by   Yuji Tokozume, et al.
The University of Tokyo

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.


page 1

page 2

page 3

page 4


Between-class Learning for Image Classification

In this paper, we propose a novel learning method for image classificati...

Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes

Data augmentation is an essential technique for improving recognition ac...

Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Features

Non-exemplar class-incremental learning refers to classifying new and ol...

Mixing Signals: Data Augmentation Approach for Deep Learning Based Modulation Recognition

With the rapid development of deep learning, automatic modulation recogn...

DropMix: Reducing Class Dependency in Mixed Sample Data Augmentation

Mixed sample data augmentation (MSDA) is a widely used technique that ha...

Distribution Networks for Open Set Learning

In open set learning, a model must be able to generalize to novel classe...

Spherical Feature Transform for Deep Metric Learning

Data augmentation in feature space is effective to increase data diversi...

Code Repositories


Chainer implementation of between-class learning for sound recognition https://arxiv.org/abs/1711.10282

view repo

Please sign up or login with your details

Forgot password? Click here to reset