Sound Event Detection Using Multiple Optimized Kernels

Xianjun Xia, Roberto Togneri, Ferdous Sohel, Yuanjun Zhao, Defeng Huang

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


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.

Original languageEnglish
Article number9103031
Pages (from-to)1745-1754
Number of pages10
JournalIEEE/ACM Transactions on Audio Speech and Language Processing
Publication statusPublished - 28 May 2020


Dive into the research topics of 'Sound Event Detection Using Multiple Optimized Kernels'. Together they form a unique fingerprint.

Cite this