University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Neuroevolution for sound event detection in real life audio: A pilot study

Kroos, Christian and Plumbley, Mark (2017) Neuroevolution for sound event detection in real life audio: A pilot study In: DCASE 2017, 16 - 17 November 2017, Munich, Germany.

kroos_neuroevolution_for_sound_event_detection_revised.pdf - Accepted version Manuscript

Download (1MB) | Preview


Neuroevolution techniques combine genetic algorithms with artificial neural networks, some of them evolving network topology along with the network weights. One of these latter techniques is the NeuroEvolution of Augmenting Topologies (NEAT) algorithm. For this pilot study we devised an extended variant (joint NEAT, J-NEAT), introducing dynamic cooperative co-evolution, and applied it to sound event detection in real life audio (Task 3) in the DCASE 2017 challenge. Our research question was whether small networks could be evolved that would be able to compete with the much larger networks now typical for classification and detection tasks. We used the wavelet-based deep scattering transform and k-means clustering across the resulting scales (not across samples) to provide J-NEAT with a compact representation of the acoustic input. The results show that for the development data set J-NEAT was capable of evolving small networks that match the performance of the baseline system in terms of the segment-based error metrics, while exhibiting a substantially better event-related error rate. In the challenge, J-NEAT took first place overall according to the F1 error metric with an F1 of 44:9% and achieved rank 15 out of 34 on the ER error metric with a value of 0:891. We discuss the question of evolving versus learning for supervised tasks.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Editors :
Virtanen, T
Mesaros, A
Heittola, T
Diment, A
Vincent, E
Benetos, E
Elizalde, B
Date : November 2017
Funders : EPRSC
Copyright Disclaimer : This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit
Uncontrolled Keywords : Sound event detection, neuroevolution, NEAT, deep scattering transform, wavelets, clustering, co-evolution
Related URLs :
Additional Information : These proceedings DCASE2017 Workshop have been published as an electronic publication of Tampere University of Technology series.
Depositing User : Melanie Hughes
Date Deposited : 10 Oct 2017 13:13
Last Modified : 11 Dec 2018 11:23

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800