Random forest classification based acoustic event detection

X. Xia; R. Togneri; F. Sohel; D. Huang

doi:10.1109/ICME.2017.8019452

Back

Conference paper

Random forest classification based acoustic event detection

X. Xia, R. Togneri, F. Sohel and D. Huang

2017 IEEE International Conference on Multimedia and Expo (ICME)

IEEE International Conference on Multimedia and Expo (ICME) 2017 (Hong Kong, China, 10/07/2017–14/07/2017)

2017

DOI: https://doi.org/10.1109/ICME.2017.8019452

Files and links (1)

url

Link to Published Version *Subscription may be requiredView

Abstract

This paper deals with the acoustic event detection (AED) to improve the detection accuracy of acoustic events. Acoustic event detection task is performed by a regression via classification (RvC) based approach along with the random forest technique. A discretization process is used to convert the continuous frame positions within acoustic events into event duration class labels. Outputs of the category-specific random forest classifiers are then reversed back to the event boundary information. Evaluations on the UPC-TALP database which consists of highly variable acoustic events demonstrate the efficiency of the proposed approaches with improvements in detection error rate compared to the best baseline system.

Details

Title: Random forest classification based acoustic event detection
Authors/Creators: X. Xia (Author/Creator) - The University of Western Australia
R. Togneri (Author/Creator) - The University of Western Australia
F. Sohel (Author/Creator)
D. Huang (Author/Creator) - The University of Western Australia
Publication Details: 2017 IEEE International Conference on Multimedia and Expo (ICME)
Conference: IEEE International Conference on Multimedia and Expo (ICME) 2017 (Hong Kong, China, 10/07/2017–14/07/2017)
Identifiers: 991005543990707891
Murdoch Affiliation: School of Engineering and Information Technology
Language: English
Resource Type: Conference paper

Metrics

92 Record Views