Label Tree Embeddings for Acoustic Scene Classification

Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins

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.
Original languageEnglish
Title of host publicationProceedings of the 2016 ACM on Multimedia Conference
Number of pages5
Place of PublicationNew York, NY, USA
PublisherACM
Publication date01.10.2016
Pages486-490
ISBN (Print)978-1-4503-3603-1
DOIs
Publication statusPublished - 01.10.2016
Event24th ACM Multimedia Conference - Amsterdam, Netherlands
Duration: 15.10.201619.10.2016
Conference number: 124107

Fingerprint

Dive into the research topics of 'Label Tree Embeddings for Acoustic Scene Classification'. Together they form a unique fingerprint.

Cite this