Label Tree Embeddings for Acoustic Scene Classification

TL;DR

This paper introduces a novel label tree embedding method for acoustic scene classification that leverages class label structures to improve feature representation, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes an automatic taxonomy learning and embedding approach that enhances acoustic scene classification performance.

Findings

Achieved state-of-the-art results on DCASE 2013 dataset.

Achieved state-of-the-art results on LITIS Rouen dataset.

Demonstrated the effectiveness of label tree embeddings in acoustic scene classification.

Abstract

We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels. Given a set of class labels, a category taxonomy is automatically learned by collectively optimizing a clustering of the labels into multiple meta-classes in a tree structure. An acoustic scene instance is then embedded into a low-dimensional feature representation which consists of the likelihoods that it belongs to the meta-classes. We demonstrate state-of-the-art results on two different datasets for the acoustic scene classification task, including the DCASE 2013 and LITIS Rouen datasets.