Fully DNN-based Multi-label regression for audio tagging

Xu, Y, Huang, Q, Wang, W, Jackson, PJB and Plumbley, MD (2016) Fully DNN-based Multi-label regression for audio tagging In: DCASE2016 Workshop (Workshop on Detection and Classification of Acoustic Scenes and Events), 2016-09-03 - 2016-09-03, Budapest, Hungary.

Preview	Text FULLY DNN-BASED MULTI-LABEL REGRESSION FOR AUDIO TAGGING.pdf - Version of Record Available under License : See the attached licence file. Download (268kB) | Preview
Preview	Text (licence) SRI_deposit_agreement.pdf Available under License : See the attached licence file. Download (33kB) | Preview

Abstract

Acoustic event detection for content analysis in most cases relies on lots of labeled data. However, manually annotating data is a time-consuming task, which thus makes few annotated resources available so far. Unlike audio event detection, automatic audio tagging, a multi-label acoustic event classification task, only relies on weakly labeled data. This is highly desirable to some practical applications using audio analysis. In this paper we propose to use a fully deep neural network (DNN) framework to handle the multi-label classification task in a regression way. Considering that only chunk-level rather than frame-level labels are available, the whole or almost whole frames of the chunk were fed into the DNN to perform a multi-label regression for the expected tags. The fully DNN, which is regarded as an encoding function, can well map the audio features sequence to a multi-tag vector. A deep pyramid structure was also designed to extract more robust high-level features related to the target tags. Further improved methods were adopted, such as the Dropout and background noise aware training, to enhance its generalization capability for new audio recordings in mismatched environments. Compared with the conventional Gaussian Mixture Model (GMM) and support vector machine (SVM) methods, the proposed fully DNN-based method could well utilize the long-term temporal information with the whole chunk as the input. The results show that our approach obtained a 15% relative improvement compared with the official GMM-based method of DCASE 2016 challenge.

Item Type:	Conference or Workshop Item (Conference Paper)
Subjects :	Electronic Engineering
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :	Name Email ORCID Xu, Y Huang, Q Wang, W Jackson, PJB Plumbley, MD
Date :	3 September 2016
Funders :	Engineering and Physical Sciences Research (EPSRC)
Copyright Disclaimer :	This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
Contributors :	Contribution Name Email ORCID Virtanen, T Mesaros, A Heittola, A Plumbley, MD Foster, P Benetos, E Lagrange, M
Uncontrolled Keywords :	Audio tagging, Deep neural networks, Multilabel regression, Dropout, DCASE 2016
Related URLs :	Publisher
Depositing User :	Symplectic Elements
Date Deposited :	20 Sep 2016 11:05
Last Modified :	11 Dec 2018 11:22
URI:	http://epubs.surrey.ac.uk/id/eprint/812240

Actions (login required)

View Item

Downloads