Generalisation in environmental sound classification : the ‘making sense of sounds’ data set and challenge

Kroos, C; Bones, OC; Cao, Y; Harris, LE; Jackson, PJB; Davies, WJ; Wang, W; Cox, TJ; Plumbley, MD

Abstract

Humans are able to identify a large number of environmental sounds and categorise them according to high-level semantic categories, e.g. urban sounds or music. They are also capable of generalising from past experience to new sounds when applying these categories. In this paper we report on the creation of a data set that is structured according to the top-level of a taxonomy derived from human judgements and the design of an associated machine learning challenge, in which strong generalisation abilities are required to be successful. We introduce a baseline classification system, a deep convolutional
network, which showed strong performance with an
average accuracy on the evaluation data of 80.8%. The result is discussed in the light of two alternative explanations: An unlikely accidental category bias in the sound recordings or a more plausible true acoustic grounding of the high-level categories.

Citation

Kroos, C., Bones, O., Cao, Y., Harris, L., Jackson, P., Davies, W., …Plumbley, M. (2019, May). Generalisation in environmental sound classification : the ‘making sense of sounds’ data set and challenge. Presented at 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019), Brighton, UK

• Presentation Conference Type: Other
• Conference Name: 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
• Conference Location: Brighton, UK
• Start Date: May 12, 2019
• End Date: May 17, 2019
• Acceptance Date: Feb 1, 2019
• Online Publication Date: Apr 17, 2019
• Publication Date: Apr 17, 2019
• Deposit Date: Mar 4, 2019
• Publicly Available Date: Jun 6, 2019
• Book Title: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
• ISBN: 9781479981311
• DOI: https://doi.org/10.1109/ICASSP.2019.8683292
• Keywords: Acoustic classification; ; Machine learning challenge; ; Sound taxonomy; ; Deep learning; ; Convolutional neural network
• Publisher URL: https://doi.org/10.1109/ICASSP.2019.8683292
• Related Public URLs: https://2019.ieeeicassp.org/; http://epubs.surrey.ac.uk/850658/
• Additional Information: Event Type : Conference; Funders : Engineering and Physical Sciences Research Council (EPSRC);European Commissions Horizon 2020; Projects : Making Sense of Sounds; Grant Number: EP/N014111/1