General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline

07/26/2018
by   Eduardo Fonseca, et al.
0

This paper describes Task 2 of the DCASE 2018 Challenge, titled "General-purpose audio tagging of Freesound content with AudioSet labels". This task was hosted on the Kaggle platform as "Freesound General-Purpose Audio Tagging Challenge". The goal of the task is to build an audio tagging system that can recognize the category of an audio clip from a subset of 41 heterogeneous categories drawn from the AudioSet Ontology. We present the task, the dataset prepared for the competition, and a baseline system.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset