The EnviSounds dataset aims to remedy the shortcomings of the existing resources. It comprises a comprehensive selection of 530 environmental sounds covering categories at different levels of complexity and different sounds produced by the same sound source. Complemented by the additional insight about sounds’ acoustic variability and norms from behavioural studies, it enables researchers to select items for experiments based on the desired categories or specific criteria across a range of acoustic features. The dataset can be used for specifying training sets with individual sound sources, defining the boundaries of various categories or providing additional variables to building prediction models. Our dataset allows for exploring long-neglected issues of within-class variability and between-class confusion by providing multiple exemplars of each class and a selection of acoustic descriptors and normative data. We believe it will be a valuable resource for behavioural and neuroimaging research.
+ +For more information or specific inquiries please contact Magdalena Kachlicka at m.kachlicka@bbk.ac.uk
+ +TBC
+ +Please get in touch if you would like to add sounds, features or have new ideas on how to expand or use the dataset.
+ +Last modified 2023/12/29
Designed by @mkachlicka
TBC.
+ +TBC.
+ +The EnviSounds dataset aims to remedy the shortcomings of the existing resources. It comprises a comprehensive selection of 530 environmental sounds covering categories at different levels of complexity and different sounds produced by the same sound source. Complemented by the additional insight about sounds’ acoustic variability and norms from behavioural studies, it enables researchers to select items for experiments based on the desired categories or specific criteria across a range of acoustic features. The dataset can be used for specifying training sets with individual sound sources, defining the boundaries of various categories or providing additional variables to building prediction models. Our dataset allows for exploring long-neglected issues of within-class variability and between-class confusion by providing multiple exemplars of each class and a selection of acoustic descriptors and normative data. We believe it will be a valuable resource for behavioural and neuroimaging research.
+Selection of the acoustic features was inspired by previous research in audio content analysis (Lerch, 2012), with emphasis on the applications in environmental sound recognition and classification (e.g., Keller & Berger, 2001; Peltonen et al., 2002; Cai et al., 2006; Muhammad & Alghatabar, 2009; Leaver & Rauschecker, 2010; Velero & Alias, 2010; for review see: Alias, Socoro, & Sevillano, 2016; Serizel, Bisot, Essid, & Richard, 2017). We included features which were shown to perform well in describing and parameterising environmental sounds. The list of selected features is not exhaustive, but based on the usefulness of those features in previous research it should provide a good starting point for considering variability in the acoustic structure of environmental sounds.
TBC.
+ +TBC.
+ +TBC.
+ +Last modified 2023/12/04
Last modified 2023/12/29
Designed by @mkachlicka