Enabling Early Audio Event Detection with Neural Networks

H. Phan, P. Koch, I. McLoughlin, A. Mertins

Abstract

This paper presents a methodology for early detection of audio events from audio streams. Early detection is the ability to infer an ongoing event during its initial stage. The proposed system consists of a novel inference step coupled with dual parallel tailored-loss deep neural networks (DNNs). The DNNs share a similar architecture except for their loss functions, i.e. weighted loss and multitask loss, which are designed to efficiently cope with issues common to audio event detection. The inference step is newly introduced to make use of the network outputs for recognizing ongoing events. The monotonicity of the detection function is required for reliable early detection, and will also be proved. Experiments on the ITC-Irst database show that the proposed system achieves state-of-the-art detection performance. Furthermore, even partial events are sufficient to achieve good performance similar to that obtained when an entire event is observed, enabling early event detection.
OriginalspracheEnglisch
Titel2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Seitenumfang5
Band 2018-April
Herausgeber (Verlag)IEEE
Erscheinungsdatum01.04.2018
Seiten141-145
ISBN (Print)978-1-5386-4659-5
ISBN (elektronisch)978-1-5386-4658-8
DOIs
PublikationsstatusVeröffentlicht - 01.04.2018
Veranstaltung2018 IEEE International Conference on Acoustics, Speech, and Signal Processing - Calgary Telus Convention Center, Calgary, Kanada
Dauer: 15.04.201820.04.2018

Fingerprint

Untersuchen Sie die Forschungsthemen von „Enabling Early Audio Event Detection with Neural Networks“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren