Introduction
This page collects basic information about all events organized by DCASE Community over the years. More detailed information is available on the each event websites. Community has concentrated its efforts on organizing evaluation workshops and challenges since 2013.
Workshops
DCASE organized workshops have brought now for two consecutive years researchers from universities and companies together to discuss about DCASE topics. The following table shows attendances from our workshops over the years:
| Workshop | Attendance (Academic / Companies) |
Papers | Acceptance rate | Challenge related papers | Total citations (Google Scholar) |
| DCASE2023 Workshop Tampere, Finland |
99 (64% / 36%) |
47 | 69% | 45% |
0
(updated 27.09.2023) |
| DCASE2022 Workshop Nancy, France |
108 (66% / 34%) |
45 | 68% | 51% |
333
(updated 30.11.2023) |
| DCASE2021 Workshop Barcelona, Spain (Virtual) |
554 (65% / 35%) |
47 | 70% | 49% |
779
(updated 30.11.2023) |
| DCASE2020 Workshop Tokyo, Japan (Virtual) |
519 (56% / 44%) |
49 | 58% | 63% |
1228
(updated 30.11.2023) |
| DCASE2019 Workshop New York, USA |
201 (50% / 50%) |
54 | 66% | 63% |
1734
(updated 30.11.2023) |
| DCASE2018 Workshop Woking, UK |
150 (62% / 38%) |
43 | 73% | 75% |
1682
(updated 30.11.2023) |
| DCASE2017 Workshop Munich, German |
90 (61% / 39%) |
27 | 90% | 82% |
1995
(updated 30.11.2023) |
| DCASE2016 Workshop Budapest, Hungary |
68 (68% / 32%) |
23 | 100% | 78% |
1280
(updated 30.11.2023) |
Challenges
The number of participating teams has increased steadily in DCASE organized challenges. The following table shows teams per task type over the years:
| Task | 2013 | 2016 | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 |
|---|---|---|---|---|---|---|---|---|---|
| Acoustic Scene Classification | 11 | 36 | 40 | 25 | 46 | 45 | 45 | 20 | 20 |
| Classification | 11 | 36 | 40 | 24 | 38 | ||||
| Mismatched recording devices | 8 | 10 | |||||||
| Multiple devices | 28 | ||||||||
| Open set | 6 | ||||||||
| Low-complexity | 30 | 31 | 20 | 20 | |||||
| Audio-visual | 14 | ||||||||
| Sound Event Detection | 7 | 18 | 20 | 15 | 18 | 21 | 24 | 29 | 23 |
| Synthetic audio | 3 | 9 | 12 | ||||||
| Real-life audio | 7 | 12 | 12 | ||||||
| Weakly supervised | 9 | 15 | 18 | 15 | |||||
| Soft labels | 8 | ||||||||
| Detection and Separation | 21 | 24 | |||||||
| Sound Event Localization and Detection | 22 | 14 | 12 | 20 | 12 | ||||
| Audio Tagging | 9 | 18 | 22 | 6 | |||||
| Tagging | 9 | 18 | 10 | 6 | |||||
| Noisy labels | 13 | ||||||||
| Bioacoustics | 11 | 8 | 15 | 5 | |||||
| Activity Classification | 12 | ||||||||
| Detection of Anomalous Sounds | 40 | 27 | 32 | 30 | |||||
| Audio Captioning | 10 | 12 | 9 | 10 | |||||
| Language-Based Audio Retrieval | 10 | 7 | |||||||
| Sound Synthesis | 16 |
2023
The eighth DCASE Workshop was organized in conjunction with DCASE 2023 Challenge. The workshop was held in Tampere on 20th-22nd of September and had 99 registered participants.
The technical program included two invited speakers: Andrew Owens (Assistant Professor at The University of Michigan), and Björn Schuller (Professor of Artificial Intelligence at Imperial College London and rofessor of Embedded Intelligence for Health Care and Wellbeing at the University of Augsburg), as well as spotlight and poster presentations of accepted papers. The full workshop proceedings are available here.
Organizers
The eighth DCASE Challenge was organized between 15th March 2023 - 1st July 2023.
Tasks
- Task 1, Low-Complexity Acoustic Scene Classification
- Task 2, First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring
- Task 3, Sound Event Localization and Detection Evaluated in Real Spatial Sound Scenes
- Task 4, Sound Event Detection with Weak Labels and Synthetic Soundscapes; Sound Event Detection with Soft Labels
- Task 5, Few-shot Bioacoustic Event Detection
- Task 6, Automated Audio Captioning and Language-Based Audio Retrieval
- Task 7, Foley Sound Synthesis
Results
Full results for all tasks can be found on the DCASE2023 Challenge page.
Participation statistics
| Teams | Entries | |
| Task 1 | 20 | 67 |
| Task 2 | 30 | 108 |
| Task 3 | 12 | 41 |
| Task 4 | 23 | 107 |
| Task 5 | 5 | 18 |
| Task 6 | 17 | 51 |
| Task 7 | 16 | 36 |
| Sum | 123 | 428 |
Organizers
Kota Dohi
Hitachi, Ltd.
Coordinator of Task 2
Tomoya Nishida
Hitachi, Ltd.
Coordinator of Task 2
Harsh Purohit
Hitachi, Ltd.
Coordinator of Task 2
Takashi Endo
Hitachi, Ltd.
Coordinator of Task 2
Yohei Kawaguchi
Hitachi, Ltd.
Coordinator of Task 2
Burooj Ghani
Coordinator of Task 5
Joe Morford
University of Oxford
Coordinator of Task 5
Michael Emmerson
Queen Mary University of London
Coordinator of Task 5
Helen Whitehead
University of Salford
Coordinator of Task 5
2022
The seventh DCASE Workshop was organized in conjunction with DCASE 2022 Challenge. The workshop was held in Nancy on 3rd-4th of November and had 110 registered participants.
The technical program included two invited speakers: Gaël Varoquaux (Research director at Inria, France), and Carina Prunkl (Research Fellow at University of Oxford, United Kingdom), as well as video and poster presentations of accepted papers. The full workshop proceedings are available here.
Organizers
The seventh DCASE Challenge was organized between 15th March 2022 - 1st July 2022.
Tasks
- Task 1, Low-Complexity Acoustic Scene Classification
- Task 2, Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques
- Task 3, Sound Event Localization and Detection Evaluated in Real Spatial Sound Scenes
- Task 4, Sound Event Detection in Domestic Environments
- Task 5, Few-shot Bioacoustic Event Detection
- Task 6, Automated Audio Captioning and Language-Based Audio Retrieval
Results
Full results for all tasks can be found on the DCASE2022 Challenge page.
Participation statistics
| Teams | Entries | |
| Task 1 | 20 | 48 |
| Task 2 | 32 | 87 |
| Task 3 | 20 | 65 |
| Task 4 | 29 | 101 |
| Task 5 | 15 | 42 |
| Task 6 | 19 | 67 |
| Sum | 135 | 410 |
Organizers
Kota Dohi
Hitachi, Ltd.
Coordinator of Task 2
Tomoya Nishida
Hitachi, Ltd.
Coordinator of Task 2
Harsh Purohit
Hitachi, Ltd.
Coordinator of Task 2
Takashi Endo
Hitachi, Ltd.
Coordinator of Task 2
Masaaki Yamamoto
Hitachi, Ltd.
Coordinator of Task 2
Yohei Kawaguchi
Hitachi, Ltd.
Coordinator of Task 2
Joe Morford
University of Oxford
Coordinator of Task 5
Michael Emmerson
Queen Mary University of London
Coordinator of Task 5
Helen Whitehead
University of Salford
Coordinator of Task 5
2021
The sixth DCASE Workshop was organized in conjunction with DCASE 2021 Challenge. The workshop was held fully virtual on 15th-19th of November and had 554 registered participants.
The technical program included two invited speakers: Laurie Heller (Professor and director of the Auditory Lab at Carnegie Mellon University), and Kristen Grauman (Professor at Department of Computer Science University of Texas at Austin and Research Director at Facebook AI Research), as well as video and poster presentations of accepted papers. The full workshop proceedings are available here.
Statistics
The full workshop statistics can be downloaded here:
Organizers
Benno Weck
Website and conference management software
Universitat Pompeu Fabra
The sixth DCASE Challenge was organized between 1st March 2021 - 1st July 2021.
Tasks
- Task 1, Acoustic scene classification
- Task 2, Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions
- Task 3, Sound Event Localization and Detection with Directional Interference
- Task 4, Sound Event Detection and Separation in Domestic Environments
- Task 5, Few-shot Bioacoustic Event Detection
- Task 6, Automated Audio Captioning
Results
Full results for all tasks can be found on the DCASE2021 Challenge page.
Participation statistics
| Teams | Entries | |
| Task 1 | 44 | 146 |
| Task 2 | 27 | 76 |
| Task 3 | 12 | 36 |
| Task 4 | 24 | 74 |
| Task 5 | 8 | 25 |
| Task 6 | 12 | 37 |
| Sum | 127 | 394 |
Organizers
Yohei Kawaguchi
Hitachi, Ltd.
Coordinator of Task 2
Kota Dohi
Hitachi, Ltd.
Coordinator of Task 2
Harsh Purohit
Hitachi, Ltd.
Coordinator of Task 2
Takashi Endo
Hitachi, Ltd.
Coordinator of Task 2
David Benvent
Coordinator of Task 5
Sripathi Sridhar
Coordinator of Task 5
2020
The fifth DCASE Workshop was organized in conjunction with DCASE 2020 Challenge. The workshop was held fully virtually on 2nd-4th of November and had a number of 519 participants.
The technical program included two invited speakers: Mounya Elhilali from Johns Hopkins University, Maryland, USA and Shin'ichi Satoh from National Institute of Informatics, Tokyo, Japan, as well as oral and poster presentations of accepted papers. The full workshop proceedings are available here.
Statistics
The full workshop statistics can be downloaded here:
Organizers
Yohei Kawaguchi
General chair
Hitachi, Ltd.
Sakiko Mishima
Industry liaison chair, diversity & inclusion chair
NEC Corporation
Sayaka Shiota
Workshop paper award chair
Tokyo Metropolitan University
Sharath Adavanne
Workshop paper award chair
Tampere University
Seongkyu Mun
Publicity chair
Samsung Research
Li Li
Publicity chair, diversity & inclusion chair
University of Tsukuba
Hanna Lukashevich
Organizing committee member
Fraunhofer Institute
Shoji Makino
Organizing committee member
University of Tsukuba
Akihiko Sugiyama
Organizing committee member
Yahoo! Japan
Kunio Kashino
Organizing committee member
NTT Corporation
Masahiro Yasuda
Organizing committee member
NTT Corporation
Takashi Endo
Organizing committee member
Hitachi, Ltd.
Harsh Purohit
Organizing committee member
Hitachi, Ltd.
Kota Dohi
Organizing committee member
Hitachi, Ltd.
Yuki Nikaido
Workshop web master
Hitachi, Ltd.
The fifth DCASE Challenge was organized between 1st March 2020 - 15th June 2020.
Tasks
- Task 1, Acoustic scene classification
- Task 2, Unsupervised Detection of Anomalous Sounds for Machine Condition Monitoring
- Task 3, Sound Event Localization and Detection
- Task 4, Sound Event Detection and Separation in Domestic Environments
- Task 5, Urban Sound Tagging with Spatiotemporal Context
- Task 6, Automated Audio Captioning
Results
Full results for all tasks can be found on the DCASE2020 Challenge page.
Participation statistics
| Teams | Entries | |
| Task 1 | 45 | 174 |
| Task 2 | 40 | 117 |
| Task 3 | 14 | 49 |
| Task 4 | 21 | 72 |
| Task 5 | 6 | 22 |
| Task 6 | 10 | 34 |
| Sum | 138 | 470 |
Organizers
Yohei Kawaguchi
Hitachi, Ltd.
Coordinator of Task 2
Toshiki Nakamura
Hitachi, Ltd.
Coordinator of Task 2
Yuki Nikaido
Hitachi, Ltd.
Coordinator of Task 2
Harsh Purohit
Hitachi, Ltd.
Coordinator of Task 2
Takashi Endo
Hitachi, Ltd.
Coordinator of Task 2
2019
The fourth DCASE Workshop was organized in conjunction with DCASE 2019 Challenge. The workshop took place in New York, USA on 25th and 26th of October and had a number of 201 participants.
The technical program included two invited speakers: Catherine Guastavino from McGill University, Montreal, Canada and Jessie Barry from Cornell University, New York, USA, as well as oral and poster presentations of accepted papers. The full workshop proceedings are available here.
Photographs by Justin Salamon, Nicolas Turpault and Toni Heittola
Organizers
The fifth DCASE Challenge was organized between 4th March 2019 - 30th June 2019.
Tasks
- Task 1, Acoustic scene classification
- Task 2, Audio tagging with noisy labels and minimal supervision
- Task 3, Sound Event Localization and Detection
- Task 4, Sound event detection in domestic environments
- Task 5, Urban Sound Tagging
Results
Full results for all tasks can be found on the DCASE2019 Challenge page.
Participation statistics
| Teams | Entries | Public leaderboard | |
| Task 1 | 46 | 146 | 139 |
| Task 2 | 13 | 27 | 880 |
| Task 3 | 22 | 58 | - |
| Task 4 | 18 | 57 | - |
| Task 5 | 10 | 23 | - |
| Sum | 109 | 311 | 1019 |
Organizers
2018
The third DCASE Workshop was organized in conjunction with DCASE 2018 Challenge. The workshop took place in Woking, Surrey, UK on 19th and 20th of November and had a number of 150 participants.
The technical program included two invited speakers: Hervé Glotin from Université de Toulon, CNRS, LIS and Hanna Lukashevich from Fraunhofer Institute for Digital Media Technology IDMT, as well as oral and poster presentations of accepted papers. The full workshop proceedings are available here.
Photographs by Christian Kroos
Organizers
The fourth DCASE Challenge was organized between 30th March 2018 - 31th July 2018.
Tasks
- Task 1, Acoustic scene classification
- Task 2, General-purpose audio tagging of Freesound content with AudioSet labels
- Task 3, Bird audio detection
- Task 4, Large-scale weakly labeled semi-supervised sound event detection in domestic environments
- Task 5, Monitoring of domestic activities based on multi-channel acoustics
Results
Full results for all tasks can be found on the DCASE2018 Challenge page.
Participation statistics
| Teams | Entries | Public leaderboard | |
| Task 1 | 25 | 77 | 102 |
| Task 2 | 18 | 36 | 558 |
| Task 3 | 11 | 28 | 68 |
| Task 4 | 15 | 48 | - |
| Task 5 | 12 | 34 | - |
| Sum | 81 | 223 | 728 |
Organizers
2017
The second DCASE Workshop was organized in conjunction with DCASE 2017 Challenge. The workshop took place in Munich on 16th and 17th of November and had a number of 90 participants (61% from academia and 39% from companies).
The technical program included two invited speakers: Shawn Hersey from Google Research and Josh McDermott from Massachusetts Institute of Technology, as well as oral and poster presentations of accepted papers. The videos an slides of the oral presentations from the workshop are available online. The full workshop proceedings are available here.
Photographs by Toni Heittola
Organizers
The third DCASE Challenge was organized between 15th March 2017 - 31th July 2017.
The challenge was organized by Tampere University of Technology in collaboration with the Carnegie Mellon University, and INRIA, and it was an official IEEE Audio and Acoustic Signal Processing (AASP) challenge. Results of the challenge were presented at the DCASE 2017 Workshop, in which selected peer-reviewed publications on challenge submission were also presented.
Tasks
- Task 1, Acoustic scene classification
- Task 2, Detection of rare sound events
- Task 3, Sound event detection in real life audio
- Task 4, Large-scale weakly supervised sound event detection for smart cars
Results
Challenge results have been published in the following journal paper:
A. Mesaros, A. Diment, B. Elizalde, T. Heittola, E. Vincent, B. Raj, and T. Virtanen. Sound event detection in the DCASE 2017 challenge. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019. In press. doi:10.1109/TASLP.2019.2907016.
Sound event detection in the DCASE 2017 Challenge
Abstract
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 was available for training. In this paper, we present the 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 difference in performance between the top systems and the baseline for all tasks.
Keywords
Event detection;Task analysis;Training;Acoustics;Speech processing;Glass;Hidden Markov models;Sound event detection;weak labels;pattern recognition;jackknife estimates;confidence intervals
Full results for all tasks can be found on the DCASE2017 Challenge website.
Participation statistics
| Participants | Submitted systems | Authors | |
| Task 1 | 39 | 97 | 129 |
| Task 2 | 13 | 33 | 38 |
| Task 3 | 13 | 36 | 32 |
| Task 4 | 9 | 34 | 25 |
| Sum | 74 | 200 | 224 |
Organizers
2016
The first DCASE Workshop was organized in conjunction with DCASE 2016 Challenge. The workshop took place in Budapest on 3rd of September 2016 and had a number of 68 participants (68% from academia and 32% from companies).
The technical program included two invited speakers: Prof. Gael Richard from Telecom Paris Tech and Dr. Sacha Krstulovic from Audio Analytic, as well as oral and poster presentations of accepted papers. The presentations from the workshop are available online. The full workshop proceedings are available here.
Photographs by Toni Heittola
Organizers
The second DCASE Challenge was organized between 8th February 2016 - 7th July 2016.
The challenge was organized by Tampere University of Technology in collaboration with the Centre for Digital Music from Queen Mary University of London, University of Surrey, and IRCCYN, and it was an official IEEE Audio and Acoustic Signal Processing (AASP) challenge. Results of the challenge were presented at the DCASE 2016 Workshop, in which selected peer-reviewed publications on challenge submission were also presented.
Tasks
- Task 1, Acoustic scene classification
- Task 2, Sound event detection in synthetic audio
- Task 3, Sound event detection in real life audio
- Task 4, Domestic audio tagging
Results
Challenge results have been published in the following journal paper:
A. Mesaros, T. Heittola, E. Benetos, P. Foster, M. Lagrange, T. Virtanen, and M. D. Plumbley. Detection and classification of acoustic scenes and events: outcome of the DCASE 2016 challenge. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26(2):379–393, Feb 2018. doi:10.1109/TASLP.2017.2778423.
Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge
Abstract
Public evaluation campaigns and datasets promote active development in target research areas, allowing direct comparison of algorithms. The second edition of the challenge on detection and classification of acoustic scenes and events (DCASE 2016) has offered such an opportunity for development of the state-of-the-art methods, and succeeded in drawing together a large number of participants from academic and industrial backgrounds. In this paper, we report on the tasks and outcomes of the DCASE 2016 challenge. The challenge comprised four tasks: acoustic scene classification, sound event detection in synthetic audio, sound event detection in real-life audio, and domestic audio tagging. We present each task in detail and analyze the submitted systems in terms of design and performance. We observe the emergence of deep learning as the most popular classification method, replacing the traditional approaches based on Gaussian mixture models and support vector machines. By contrast, feature representations have not changed substantially throughout the years, as mel frequency-based representations predominate in all tasks. The datasets created for and used in DCASE 2016 are publicly available and are a valuable resource for further research.
Keywords
Acoustics;Event detection;Hidden Markov models;Speech;Speech processing;Tagging;Acoustic scene classification;audio datasets;pattern recognition;sound event detection
Full results for all tasks can be found also on the DCASE2016 Challenge website.
Participation statistics
| Participants | Submitted systems | Authors | Affiliations | |
| Task 1 | 35 | 49 | 115 | 55 |
| Task 2 | 10 | 11 | 40 | 14 |
| Task 3 | 13 | 17 | 46 | 21 |
| Task 4 | 9 | 8 | 23 | 8 |
| Sum | 67 | 84 | 224 | 98 |
| Unique | - | - | 158 | 79 |
Organizers
2013
DCASE 2013 Challenge
The first DCASE challenge campaign was organized between 31st March 2013 - 14th April 2013. The challenge was organized by the Centre for Digital Music and by IRCAM, under the auspices of the Audio and Acoustic Signal Processing (AASP) technical committee of the IEEE Signal Processing Society.
Results were presented at a special session in WASPAA 2013; participants were also invited to present a poster at a special session.
Tasks
- Task 1, Acoustic scene classification
- Task 2, Sound event detection, Office Live and Office Synthetic
Results
The outcomes of the DCASE 2013 challenge are now fully described in the following open-access journal article:
D. Stowell, D. Giannoulis, E. Benetos, M. Lagrange, and M.D. Plumbley. Detection and classification of acoustic scenes and events. Multimedia, IEEE Transactions on, 17(10):1733–1746, Oct 2015. doi:10.1109/TMM.2015.2428998.
Detection and Classification of Acoustic Scenes and Events
Abstract
For intelligent systems to make best use of the audio modality, it is important that they can recognise not just speech and music, which have been researched as specific tasks, but also general sounds in everyday environments. To stimulate research in this field we conducted a public research challenge: the IEEE Audio and Acoustic Signal Processing Technical Committee challenge on Detection and Classification of Acoustic Scenes and Events (DCASE). In this paper we report on the state of the art in automatically classifying audio scenes, and automatically detecting and classifying audio events. We survey prior work as well as the state of the art represented by the submissions to the challenge from various research groups. We also provide detail on the organisation of the challenge, so that our experience as challenge hosts may be useful to those organising challenges in similar domains. We created new audio datasets and baseline systems for the challenge: these, as well as some submitted systems, are publicly available under open licenses, to serve as benchmark for further research in general-purpose machine listening.
Keywords
Event detection;Licenses;Microphones;Music;Speech;Speech recognition
Participation statistics
| Participants | |
| Task 1 | 11 |
| Task 2 | 7 |
| Task 3 | 3 |
| Sum | 21 |
