@inbook{839a2d44393c46a3991fba9543dbf717, author = "Tuomas Virtanen and Mark D. Plumbley and Dan Ellis", abstract = "Developing computational systems requires methods for evaluating their performance to guide development and compare alternate approaches. A reliable evaluation procedure for a classification or recognition system will involve a standard dataset of example input data along with the intended target output, and well-defined metrics to compare the systems' outputs with this ground truth. This chapter examines the important factors in the design and construction of evaluation datasets and goes through the metrics commonly used in system evaluation, comparing their properties. We include a survey of currently available datasets for environmental sound scene and event recognition and conclude with advice for designing evaluation protocols.", booktitle = "Computational Analysis of Sound Scenes and Events", doi = "10.1007/978-3-319-63450-0_1", editor = "Tuomas Virtanen and Mark D. Plumbley and Dan Ellis", isbn = "978-3-319-63449-4", month = "9", pages = "3--12", publisher = "Springer", title = "{I}ntroduction to sound scene and event analysis", year = "2017", }