Generalisation in Environmental Sound Classification: The 'Making Sense of Sounds' Data Set and Challenge
Christian Kroos, Oliver Bones, Yin Cao, Lara Harris, Philip J. B. Jackson, William J. Davies, Wenwu Wang, Trevor J. Cox
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.
BibTeX
@inproceedings{icassp2019_generalisationin,
title = {Generalisation in Environmental Sound Classification: The 'Making Sense of Sounds' Data Set and Challenge},
author = {Christian Kroos and Oliver Bones and Yin Cao and Lara Harris and Philip J. B. Jackson and William J. Davies and Wenwu Wang and Trevor J. Cox and Mark D. Plumbley},
booktitle = {ICASSP 2019},
year = {2019}
}