Unifying Isolated and Overlapping Audio Event Detection with Multi-label Multi-task Convolutional Recurrent Neural Networks

Huy Phan, Oliver Y. Chen, Philipp Koch, Lam Pham, Ian McLoughlin, Alfred Mertins, Maarten De Vos

Abstract

We propose a multi-label multi-task framework based on a convolutional recurrent neural network to unify detection of isolated and overlapping audio events. The framework leverages the power of convolutional recurrent neural network architectures; convolutional layers learn effective features over which higher recurrent layers perform sequential modelling. Furthermore, the output layer is designed to handle arbitrary degrees of event overlap. At each time step in the recurrent output sequence, an output triple is dedicated to each event category of interest to jointly model event occurrence and temporal boundaries. That is, the network jointly determines whether an event of this category occurs, and when it occurs, by estimating onset and offset positions at each recurrent time step. We then introduce three sequential losses for network training: multi-label classification loss, distance estimation loss, and confidence loss. We demonstrate good generalization on two datasets: ITC-Irst for isolated audio event detection, and TUT-SED-Synthetic-2016 for overlapping audio event detection.

Original languageEnglish
Title of host publicationICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Number of pages5
PublisherIEEE
Publication date05.2019
Pages51-55
Article number8683064
ISBN (Print)978-1-4799-8132-8
ISBN (Electronic)978-1-4799-8131-1
DOIs
Publication statusPublished - 05.2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing - Brighton Conference Centre, Brighton, United Kingdom
Duration: 12.05.201917.05.2019
Conference number: 149034

Fingerprint

Dive into the research topics of 'Unifying Isolated and Overlapping Audio Event Detection with Multi-label Multi-task Convolutional Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this