Publications

Here you can find the list of my publications, as well as the resources associated with them (e.g. slideshows or posters used at conferences, and code when available). You can also check my list of publications on Google Scholar.

2021

Training Sound Event Classifiers Using Different Types of Supervision
Eduardo Fonseca
PhD Thesis, Universitat Pompeu Fabra, 2021
[PDF] [slides] [video]

Self-Supervised Learning from Automatically Separated Sound Scenes
E. Fonseca, A. Jansen, D. P. W. Ellis, S. Wisdom, M. Tagliasacchi, J. R. Hershey, M. Plakal, S. Hershey, R. C. Moore, X. Serra
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New York, USA, 2021
[PDF] [slides] [video]
This paper received the “Best Audio Representation Learning Paper Award” at WASPAA 2021.

Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks
E. Fonseca, A. Ferraro, X. Serra
Under review. arXiv:2107.00623, 2021
[PDF] [code soon]

Unsupervised Contrastive Learning of Sound Event Representations
E. Fonseca, D. Ortego, K. McGuinness, N.E. O’Connor, X. Serra
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
[PDF] [code] [slides] [poster] [blog post] [video]

The Benefit of Temporally-Strong Labels in Audio Event Classification
S. Hershey, D. PW Ellis, E. Fonseca, A. Jansen, C. Liu, R C. Moore, M. Plakal
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
[PDF]

What’s All the FUSS About Free Universal Sound Separation Data?
S. Wisdom, H. Erdogan, D. P.W. Ellis, R. Serizel, N. Turpault, E. Fonseca, J. Salamon, P. Seetharaman, J. Hershey
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
[PDF]

Sound Event Detection and Separation: a Benchmark on DESED Synthetic Soundscapes
N. Turpault, R. Serizel, S. Wisdom, H. Erdogan, J. Hershey, E. Fonseca, P. Seetharaman, J. Salamon
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
[PDF]

Toward interpretable polyphonic sound event detection with attention maps based on local prototypes
P. Zinemanas, M. Rocamora, E. Fonseca, F. Font, X. Serra
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, Barcelona, Spain, 2021
[PDF]

FSD50K: an Open Dataset of Human-Labeled Sound Events
E. Fonseca, X. Favory, J. Pons, F. Font, and X. Serra.
IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol 30, 2022
[PDF] [FSD50K dataset] [code] [companion site]

2020

Addressing Missing Labels in Large-scale Sound Event Recognition using a Teacher-student Framework with Loss Masking
E. Fonseca, S. Hershey, M. Plakal, D. P. W. Ellis, A. Jansen, and R. C. Moore.
In IEEE Signal Processing Letters, Vol. 27, pages 1235 - 1239, 2020
[ArXiv][IEEEXplore]

Improving Sound Event Detection In Domestic Environments Using Sound Separation
N. Turpault, S. Wisdom, H. Erdogan, J. Hershey, R. Serizel, E. Fonseca, P. Seetharaman, J. Salamon
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, Tokyo, Japan, 2020
[PDF]

2019

Model-agnostic Approaches to Handling Noisy Labels when Training Sound Event Classifiers
E. Fonseca, F. Font, and X. Serra
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New York, USA, 2019
[PDF] [code] [slides]

Audio tagging with noisy labels and minimal supervision
E. Fonseca, M. Plakal, F. Font, D. P. W. Ellis, and X. Serra
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, NYC, USA, 2019
[PDF] [code] [FSDKaggle2019 dataset] [poster]

A Hybrid Parametric-Deep Learning Approach for Sound Event Localization and Detection
A. Perez, E. Fonseca, and X. Serra
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, NYC, USA, 2019
[PDF] [code]

Learning Sound Event Classifiers from Web Audio with Noisy Labels
E. Fonseca, M. Plakal, D. P. W. Ellis, F. Font, X. Favory, and X. Serra
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, 2019
[PDF] [code] [FSDnoisy18k dataset] [slides]

2018

Facilitating the Manual Annotation of Sounds When Using Large Taxonomies
X. Favory, E. Fonseca, F. Font, and X. Serra
Proceedings of the 23rd Conference of Open Innovations Association FRUCT, 2018
[PDF] [code]

General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline E. Fonseca, M. Plakal, F. Font, D. P. W. Ellis, X. Favory, J. Pons, and X. Serra
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, Surrey, UK, 2018
[PDF] [code] [FSDKaggle2018 dataset] [poster]

A Simple Fusion of Deep and Shallow Learning for Acoustic Scene Classification
E. Fonseca, R. Gong, and X. Serra
Sound & Music Computing Conference (SMC), Limassol, Cyprus, 2018
[PDF] [poster]

2017

Freesound Datasets: A Platform for the Creation of Open Audio Datasets
E. Fonseca, J. Pons, X. Favory, F. Font, D. Bogdanov, A. Ferraro, S. Oramas, A. Porter, and X. Serra
International Society for Music Information Retrieval Conference (ISMIR), Suzhou, China, 2017
[PDF] [code] [Freesound Annotator] [poster]

Acoustic Scene Classification by Ensembling Gradient Boosting Machine and Convolutional Neural Networks
E. Fonseca, R. Gong, D. Bogdanov, O. Slizovskaia, E. Gomez, and X. Serra
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, Munich, Germany, 2017
[PDF] [slides]

Acoustic Scene Classification by Fusing LightGBM and VGG-net Multichannel Predictions
R. Gong, E. Fonseca, D. Bogdanov, O. Slizovskaia, E. Gomez, and X. Serra
Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge, 2017
[PDF]

Oldies

Inclusion of Phase Information into the Image Source Method
E. Fonseca (Master thesis)
Aalborg University, MSc in Acoustics Engineering, 2009
[PDF]