LGSDASMLNov 28, 2017

Learning from Between-class Examples for Deep Sound Recognition

arXiv:1711.10282v2265 citations
Originality Highly original
AI Analysis

This addresses the challenge of enhancing discriminative feature learning in sound recognition, offering a novel training strategy that consistently boosts performance across different setups.

The authors tackled the problem of improving deep sound recognition by proposing Between-Class learning (BC learning), a method that trains models to recognize mixed sounds from different classes, resulting in performance that surpasses human-level accuracy on various datasets and networks.

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.

Code Implementations5 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes