DCASE2020 Workshop, Call for Papers

Workshop on Detection and Classification of Acoustic Scenes and Events
2-3 November 2020, Tokyo, Japan (full virtual)

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 5th Workshop on Detection and Classification of Acoustic Scenes and Events, DCASE 2020, will be held FULLY VIRTUALLY on November 2-3, 2020.

This is the first DCASE workshop held in Asia, following previous successful events held in Budapest (2016), Munich (2017), Surrey (2018) and New York City (2019). The workshop, in combination with Interspeech 2020 hosted in Shanghai in the previous week, offers two weeks of exciting audio and speech related events!

As in the 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 topics, and provide an opportunity for scientific exchange of ideas and opinions. The technical program will include invited talks, and oral and poster presentations of accepted papers. In addition, a special poster session will be dedicated to the DCASE 2020 challenge entries and results.

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 and event detection
  • Anomalous sound detection
  • Sound event detection and localization
  • Sound event detection and separation
  • Audio tagging
  • Automated audio captioning
  • 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, material science, transport science

Resources, applications, and evaluations 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 2020 Challenge, expanded from the challenge technical report submissions to include more discussions such as ablation studies for additional modules in your method.

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

Important notice for challenge participants: Note that whereas each DCASE challenge submission must be accompanied by a technical report describing the system, in order to be considered for presentation at the peer-reviewed workshop, such a report must be augmented with a careful analysis thereof to guarantee fair conditions to non-challenge submissions which provide meaningful and usable insight.

 

Important Dates

The DCASE 2020 Workshop Organizers wish to announce that after careful consideration and discussion, we have decided to change the date of DCASE workshop to November 2-3. The purpose of rescheduling is to avoid the overlap with the INTERSPEECH 2020 (Oct. 25-29) and to make it easy to participate in both INTERSPEECH and DCASE. We believe that these two weeks will become more exciting for DCASE researchers.

Organizers

General chairs

Nobutaka Ono
Nobutaka Ono

Tokyo Metropolitan University

Noboru Harada
Noboru Harada

NTT Corporation

Yohei Kawaguchi
Yohei Kawaguchi

Hitachi, Ltd.

Program chairs

Annamaria Mesaros
Annamaria Mesaros

Tampere University

Yuma Koizumi
Yuma Koizumi

NTT Corporation

Keisuke Imoto
Keisuke Imoto

Doshisha University

Tatsuya Komatsu
Tatsuya Komatsu

LINE Corporation

Venue

A virtual platform