Logo image
Back
Sound event detection using multiple optimized kernels
Journal article   Peer reviewed

Sound event detection using multiple optimized kernels

X. Xia, R. Togneri, F. Sohel, Y. Zhao and D. Huang
IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol.28, pp.1745-1754
2020
DOI: https://doi.org/10.1109/TASLP.2020.2998298
url
Link to Published Version *Subscription may be requiredView

Abstract

Sound event detection (SED) has been widely applied in real world applications. Convolutional recurrent neural network based SED approaches have achieved state-of-the-art performance. However, the convolution process is typically performed by using a fixed sized kernel, which adversely affects the detection accuracy especially when the acoustic features of different event classes are characterized by high variations. To deal with this, this article proposes a sound event detection technique using a convolutional recurrent neural network framework with multiple convolutional kernels of different sizes. The top performing kernels are selected from a kernel pool based on the unsupervised clustering errors and the accuracies of the temporarily trained models. Afterwards, the selected kernels are fed to multiple convolution layers to deal with the acoustic feature variations. Experimental results on different subsets of AudioSet, namely the DCASE Challenge 2017 Task 4 and DCASE Challenge 2018 Task 4, demonstrate the performance of the proposed approach compared to state-of-the-art systems.

Details

Metrics

42 Record Views
6 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types
Domestic collaboration
Citation topics
4 Electrical Engineering, Electronics & Computer Science
4.174 Digital Signal Processing
4.174.152 Speech Recognition
Web Of Science research areas
Acoustics
Engineering, Electrical & Electronic
ESI research areas
Engineering
Logo image