dcase_util, a python library for DCASE researcher, has been published. The library is a collection of utilities created for Detection and Classification of Acoustic Scenes and Events (DCASE). These utilities were originally created for the DCASE challenge baseline systems (2016 & 2017) and are bundled now into a standalone library to allow their re-usage in other research projects. At the same time, the code has been polished and some inconsistencies have been smoothed out.

The main goal of these utilities is to streamline the research code, make it a bit more readable, and easier to maintain. Most of the currently implemented utilities are related to audio datasets: handling meta data and various forms of other structured data, and provide standardized usage API to audio datasets from various sources. In addition to this, there is large amount of general utilities to help handling files, printing and logging information while application is running, and streamlining the acoustic feature extraction. More detailed information about the library and tutorials how to use it can be found in the documentation.

I hope researchers in the DCASE community find the utilities helpful, and contribute ideas of other useful utilities back to community through dcase_util.