Phan, Huy, Hertel, Lars, Maass, Marco, Koch, Philipp, Mertins, Alfred (2016) Label Tree Embeddings for Acoustic Scene Classification. In: Proceedings of the 24th ACM international conference on Multimedia. . pp. 486-490. ACM, Amsterdam, The Netherlands ISBN 978-1-4503-3603-1. (doi:10.1145/2964284.2967268) (KAR id:72682)
|
PDF
Author's Accepted Manuscript
Language: English |
|
|
Download this file (PDF/200kB) |
Preview |
| Request a format suitable for use with assistive technology e.g. a screenreader | |
| Official URL: http://dx.doi.org/10.1145/2964284.2967268 |
|
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.
| Item Type: | Conference or workshop item (Proceeding) |
|---|---|
| DOI/Identification number: | 10.1145/2964284.2967268 |
| Institutional Unit: | Schools > School of Computing |
| Former Institutional Unit: |
Divisions > Division of Natural Sciences > School of Computing Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
|
| Depositing User: | Huy Phan |
| Date Deposited: | 25 Feb 2019 16:16 UTC |
| Last Modified: | 20 May 2025 10:23 UTC |
| Resource URI: | https://kar.kent.ac.uk/id/eprint/72682 (The current URI for this page, for reference purposes) |
University of Kent Author Information
Phan, Huy.
| Creator's ORCID: |
 https://orcid.org/0000-0003-4096-785X
|
|---|---|
| CReDIT Contributor Roles: |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):
Altmetric
Altmetric
