Sound Event Detection in the DCASE 2017 Challenge

Annamaria Mesaros, Aleksandr Diment, Benjamin Elizalde, Toni Heittola, Emmanuel Vincent, Bhiksha Raj, Tuomas Virtanen

Research output: Contribution to journalArticleScientificpeer-review

88 Citations (Scopus)
2 Downloads (Pure)


Each edition of the challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) contained several tasks involving sound event detection in different setups. DCASE 2017 presented participants with three such tasks, each having specific datasets and detection requirements: Task 2, in which target sound events were very rare in both training and testing data, Task 3 having overlapping events annotated in real-life audio, and Task 4, in which only weakly labeled data were available for training. In this paper, we present three tasks, including the datasets and baseline systems, and analyze the challenge entries for each task. We observe the popularity of methods using deep neural networks, and the still widely used mel frequency-based representations, with only few approaches standing out as radically different. Analysis of the systems behavior reveals that task-specific optimization has a big role in producing good performance; however, often this optimization closely follows the ranking metric, and its maximization/minimization does not result in universally good performance. We also introduce the calculation of confidence intervals based on a jackknife resampling procedure to perform statistical analysis of the challenge results. The analysis indicates that while the 95% confidence intervals for many systems overlap, there are significant differences in performance between the top systems and the baseline for all tasks.

Original languageEnglish
Pages (from-to)992-1006
Number of pages15
JournalIEEE/ACM Transactions on Audio Speech and Language Processing
Issue number6
Publication statusPublished - 1 Jun 2019
Publication typeA1 Journal article-refereed


  • confidence intervals
  • jackknife estimates
  • pattern recognition
  • Sound event detection
  • weak labels

Publication forum classification

  • Publication forum level 3

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Acoustics and Ultrasonics
  • Computational Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Sound Event Detection in the DCASE 2017 Challenge'. Together they form a unique fingerprint.

Cite this