DCASE2019 Workshop

Workshop on Detection and Classification of Acoustic Scenes and Events
25-26 October 2019, New York, USA

The workshop aims to provide a venue for researchers working on computational analysis of sound events and scene analysis to present and discuss their results.

The 4th Workshop on Detection and Classification of Acoustic Scenes and Events, DCASE 2019, will be held in New York City on October 25-26 2019.

As in previous years the workshop is organized in conjunction with the DCASE challenge. We aim to bring together researchers from many different universities and companies with an interest in the topic, and provide the opportunity for scientific exchange of ideas and opinions.

The technical program will include invited speakers on the topic of computational everyday sound analysis and recognition, and oral and poster presentations of accepted papers. In addition, a special poster session will be dedicated to the DCASE 2019 challenge entries and results.

Note that the workshop immediately follows WASPAA 2019 and SANE 2019, also hosted in New York, offering a full week of exciting audio related research!

Topics

We invite submissions on the topics of computational analysis of acoustic scenes and sound events, including but not limited to:

Tasks in computational environmental audio analysis

  • Acoustic scene classification
  • Sound event detection and localization
  • Audio tagging
  • Challenges in real-life applications (e.g., rare events, overlapping sound events, weak labels)

Methods for computational environmental audio analysis

  • Signal processing methods
  • Machine learning methods
  • Auditory-motivated methods
  • Cross-disciplinary methods involving, e.g., acoustics, biology, psychology, geography, materials science, transports science

Resources, applications, and evaluation of computational environmental audio analysis

  • Publicly available datasets or software, taxonomies and ontologies, evaluation procedures
  • Ethics, privacy, responsible research
  • Applications
  • Description of systems submitted to the DCASE 2019 Challenge, expanded from the challenge technical report submissions to include evaluation results and comparison.

Reproducible research with open-source code and open data is encouraged (but not mandatory).

 

 

Program Overview

Full program here

 

Day 1   Friday 25/10/2019, 8:30 - 17:25

8:30 Registration &
Breakfast
9:20 Welcome

Juan Pablo Bello
New York University

9:30 Keynote

Making sense of the sounds around us: Auditory scene analysis in everyday listening

Catherine Guastavino

McGill University, School of Information Studies

10:20 Challenge
spotlights

Reports on the 5 tasks of the DCASE 2019 challenge

10:50 Coffee/Tea
11:20 Oral session I

Acoustic Scene and Robust Classification
4 presentations

12:40 Lunch
13:40 Poster session I

Workshop papers and reports on challenge tasks
23 posters

15:10 Coffee/Tea
15:40 Oral session II

Audio Tagging and Weak Supervision
4 presentations

17:00 Challenge awards
17:15 Paper awards
17:20 DCASE 2020 announcements
17:25 End of sessions

Day 2   Saturday 26/10/2019, 8:30 - 17:00

8:30 Arrival &
Breakfast
9:20 Keynote

Deep learning meets public tools to inspire the protection of nature

Jessie Barry

Cornell University, The Cornell Lab of Ornithology

10:10 Oral session III

Audio Captioning
2 presentations

10:50 Coffee/Tea
11:20 Oral session IV

Sound Event Detection and Localization
4 presentations

12:40 Lunch
13:40 Poster session II

Workshop papers
24 posters

15:10 Coffee/Tea
15:40 Town hall discussion
16:40 Closing remarks
17:00 End of workshop

17:40 - 19:40   Welcome Reception

370 Jay St, 12th Floor

Venue

New York University's Tandon School of Engineering, Brooklyn, NY, USA.

Important Dates