Phan, Huy, Chén, Oliver Y., Koch, Philipp, Pham, Lam Dang, McLoughlin, Ian, Mertins, Alfred, De Vos, Maarten (2019) Beyond Equal-Length Snippets: How Long is Sufficient to Recognize an Audio Scene? In: AES E-LIBRARY. 2019 AES Conference on Audio Forensics. . The Audio Engineering Society (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:73780)
PDF
Author's Accepted Manuscript
Language: English Restricted to Repository staff only |
|
Contact us about this Publication
|
|
Official URL: http://www.aes.org/e-lib/browse.cfm?elib=20468 |
Abstract
Due to the variability in characteristics of audio scenes, some scenes can naturally be recognized earlier than others. In this work, rather than using equal-length snippets for all scene categories, as is common in the literature, we study to which temporal extent an audio scene can be reliably recognized given state-of-the-art models. Moreover, as model fusion with deep network ensemble is prevalent in audio scene classification, we further study whether, and if so, when model fusion is necessary for this task. To achieve these goals, we employ two single-network systems relying on a convolutional neural network and a recurrent neural network for classification as well as early fusion and late fusion of these networks. Experimental results on the LITIS-Rouen dataset show that some scenes can be reliably recognized with a few seconds while other scenes require significantly longer durations. In addition, model fusion is shown to be the most beneficial when the signal length is short.
Item Type: | Conference or workshop item (Paper) |
---|---|
Uncontrolled keywords: | Audio scene recognition, early recognition, convolutional neural network, recurrent neural network, model fusion |
Subjects: | T Technology |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
Depositing User: | Huy Phan |
Date Deposited: | 07 May 2019 12:43 UTC |
Last Modified: | 05 Nov 2024 12:36 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/73780 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):