2014/11/13 by Daniele Barchiesi, Dimitrios Giannoulis, Dan Stowell +1 · 1 citation
Computer Science · #Artificial intelligence #Benchmark (surveying) #Computer science #Data mining #Data set #Implementation #Machine learning #Music Technology and Sound Studies #Music and Audio Processing #Pattern recognition (psychology) #Range (aeronautics) #Set (abstract data type) #Speech and Audio Processing #Speech recognition #Task (project management) #cs.LG #cs.SD
paper · pdf · doi:10.1109/msp.2014.2326181
published as IEEE Signal Processing Magazine 32(3) (May 2015) 16-34
arxiv created 2014/11/13 · openalex publication_date 2015/04/03 · arxiv updated 2015/04/08 · openalex created_date 2016/06/24 · openalex updated_date 2026/08/06
In this article, we present an account of the state of the art in acoustic scene classification (ASC), the task of classifying environments from the sounds they produce. Starting from a historical review of previous research in this area, we define a general framework for ASC and present different implementations of its components. We then describe a range of different algorithms submitted for a data challenge that was held to provide a general and fair benchmark for ASC techniques. The data set recorded for this purpose is presented along with the performance metrics that are used to evaluate the algorithms and statistical significance tests to compare the submitted methods.