Auxiliary Classifier Generative Adversarial Network With Soft Labels in Imbalanced Acoustic Event Detection

In acoustic event detection, the training data size of some acoustic events is often small and imbalanced. To deal with this, this paper proposes generating the virtual training data categorically using the auxiliary classifier generative adversarial networks. Soft labels of acoustic events are firs...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2019-06, Vol.21 (6), p.1359-1371
Main Authors: Xia, Xianjun, Togneri, Roberto, Sohel, Ferdous, Huang, Defeng
Format: Article
Language:English
Subjects:
Acoustic event detection
Acoustics
auxiliary classifier generative adversarial networks
Classifiers
Event detection
Feature extraction
Generative adversarial networks
Hidden Markov models
Labels
Localization
quantized confidence measure
Training
Training data
Virtual networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In acoustic event detection, the training data size of some acoustic events is often small and imbalanced. To deal with this, this paper proposes generating the virtual training data categorically using the auxiliary classifier generative adversarial networks. Soft labels of acoustic events are first calculated to represent the acoustic event localization information. The closer the current frame is to the middle of the manually labeled acoustic event, the higher the soft label will be, which makes the soft labels positively correlated with the acoustic event localization. Then, the acoustic event class and the quantized soft labels are used as the input condition to the auxiliary classifier generative adversarial networks to generate an arbitrary number of training samples. Experimental results on the TUT Sound Event 2016 under the home environment and TUT Sound Event 2017 under the street environment demonstrate the improved performance of the proposed technique compared to existing acoustic event detection systems.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2018.2879750