Positive and negative sampling strategies for self-supervised learning on audio-video data
S. Wang, S. Tripathy, T. Heittola, A. Mesaros
IEEE ICASSP 2024 workshop Self-supervision in Audio, Speech and Beyond, Seoul, South Korea
Publications
2024
Class-Incremental Learning for Multi-Label Audio Classification
M Mulimani, A Mesaros
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, south Korea
2023
Binaural Sound Source Distance Estimation and Localization for a Moving Listener
DA Krause, G García-Barrios, A Politis, A Mesaros
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 996-1011, 2024, doi: 10.1109/TASLP.2023.3346297
Evaluating classification systems against soft labels with fuzzy precision and recall
Manu Harju, Annamaria Mesaros
8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023), Tampere, Finland
Incremental Learning of Acoustic Scenes and Sound Events
Manjunath Mulimani, Annamaria Mesaros
8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023), Tampere, Finland
Sound event classification with object-based labels
James Afolaranmi, Irene Martin, Annamaria Mesaros
8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023), Tampere, Finland
Training sound event detection with soft labels from crowdsourced annotations
I. Martín-Morató, M. Harju, P. Ahokas, A. Mesaros
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greece
Aggregate or separate: learning from multi-annotator noisy labels for best classification performance
Irene Martín-Morató, Paul Ahokas, Annamaria Mesaros
8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023), Tampere, Finland
Self-supervised learning of audio representations using angular contrastive loss
S. Wang, S. Tripathy, A. Mesaros
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greece
Strong labeling of sound events using crowdsourced weak labels and annotator competence estimation
Irene Martín-Morató, Annamaria Mesaros
IEEE/ACM Transactions on Audio, Speech, and Language Processing, VOL. 31, 2023, DOI 10.1109/TASLP.2022.3233468
2022
A Summarization Approach to Evaluating Audio Captioning
Irene Martin Morato, Manu Harju, Annamaria Mesaros
7th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2022), Nancy, France
Low-Complexity Acoustic Scene Classification in DCASE 2022 Challenge
Irene Martin-Morato, Francesco Paissan, Alberto Ancilotto, Toni Heittola, Annamaria Mesaros, Elisabetta Farella, Alessio Brutti, and Tuomas Virtanen
7th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2022), Nancy, France
Binaural source localization using deep learning and head rotation information
Guillermo Garcıa-Barrios, Daniel Aleksander Krause, Archontis Politis, Annamaria Mesaros, Juana M. Gutierrez-Arriola, Ruben Fraile
30th European Signal Processing Conference (EUSIPCO 2022). Belgrade, Serbia
Binaural Signal Representations for Joint Sound Event Detection and Acoustic Scene Classification
Daniel Aleksander Krause, Annamaria Mesaros
30th European Signal Processing Conference (EUSIPCO 2022). Belgrade, Serbia
Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment
Shanshan Wang, Archontis Politis, Annamaria Mesaros, and Tuomas Virtanen
IEEE Journal of Selected Topics in Signal Processing, 2022, doi: 10.1109/JSTSP.2022.3180592.
2021
Diversity and Bias in Audio Captioning Datasets
Irene Martin and Annamaria Mesaros
Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)
Audio-visual scene classification: analysis of DCASE 2021 Challenge submissions
Shanshan Wang, Toni Heittola, Annamaria Mesaros, Tuomas Virtanen
In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021). Barcelona, Spain (online), Nov 2021.
Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems
Irene Martín-Morató, Toni Heittola, Annamaria Mesaros, Tuomas Virtanen
In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021). Barcelona, Spain (online), Nov 2021.
Sound event detection: a tutorial
Annamaria Mesaros, Toni Heittola, Tuomas Virtanen, Mark D. Plumbley
IEEE Signal Processing Magazine, vol. 38, no. 5, pp. 67-83, Sept. 2021,
doi:10.1109/MSP.2021.3090678.
Crowdsourcing strong labels for sound event detection
Irene Martin Morato, Manu Harju, Annamaria Mesaros
In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2021). New Paltz, NY, Oct 2021.
Joint direction and proximity classification of overlapping sound events from binaural audio
Daniel Aleksander Krause, Archontis Politis, Annamaria Mesaros
In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2021). New Paltz, NY, Oct 2021.
What is the ground truth? Reliability of multi-annotator data for audio tagging
Irene Martin-Morato, Annamaria Mesaros
29th European Signal Processing Conference, EUSIPCO 2021
Dataset download link:10.5281/zenodo.4774959
A curated dataset of urban acoustic scenes for audio-visual scene analysis
Shanshan Wang, Annamaria Mesaros, Toni Heittola, and Tuomas Virtanen
In 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Dataset download link:10.5281/zenodo.4477542
Overview and evaluation of sound event localization and detection in DCASE 2019
Archontis Politis, Annamaria Mesaros, Sharath Adavanne, Toni Heittola, and Tuomas Virtanen
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29():684–698, 2021. doi:10.1109/TASLP.2020.3047233.
2020
Acoustic scene classification in DCASE 2020 challenge: generalization across devices and low complexity solutions
Toni Heittola, Annamaria Mesaros, and Tuomas Virtanen
In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020),
2019
Acoustic scene classification in DCASE 2019 challenge: closed and open set classification and data mismatch setups
Annamaria Mesaros, Toni Heittola, and Tuomas Virtanen
In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019)
City classification from multiple real-world sound scenes
Helen L. Bear, Toni Heittola, Annamaria Mesaros, Emmanouil Benetos, and Tuomas Virtanen
In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
Joint measurement of localization and detection of sound events
Annamaria Mesaros, Sharath Adavanne, Archontis Politis, Toni Heittola, and Tuomas Virtanen
In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
Audio-based epileptic seizure dectection
Istiaq M.N Ahsan, Csaba Kertesz, Annamaria Mesaros, Toni Heittola, Andrew Knight, and Tuomas Virtanen
In 27th European Signal Processing Conference 2019 (EUSIPCO 2019)
Sound event detection in the DCASE 2017 Challenge
Annamaria Mesaros, Aleksandr Diment, Benjamin Elizalde, Toni Heittola, Emmanuel Vincent, Bhiksha Raj, and Tuomas Virtanen
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(6):992–1006, June 2019. doi:10.1109/TASLP.2019.2907016
Sound event envelope estimation in polyphonic mixtures
Irene Martin-Morato, Annamaria Mesaros, Toni Heittola, Tuomas Virtanen, Maximo Cobos, and Francesc J. Ferri
In 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)