Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Xavier Serra

Emotion Embedding Spaces for Matching Music to Stories


Nov 26, 2021
Minz Won, Justin Salamon, Nicholas J. Bryan, Gautham J. Mysore, Xavier Serra

* International Society for Music Information Retrieval (ISMIR) 2021, Best Student Paper 

  Access Paper or Ask Questions

Semi-Supervised Music Tagging Transformer


Nov 26, 2021
Minz Won, Keunwoo Choi, Xavier Serra

* International Society for Music Information Retrieval (ISMIR) 2021 

  Access Paper or Ask Questions

Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning


Oct 14, 2021
Benno Weck, Xavier Favory, Konstantinos Drossos, Xavier Serra

* 5 pages, 4 figures. Accepted at Detection and Classification of Acoustic Scenes and Events 2021 (DCASE2021) 

  Access Paper or Ask Questions

Soundata: A Python library for reproducible use of audio datasets


Oct 04, 2021
Magdalena Fuentes, Justin Salamon, Pablo Zinemanas, Mart铆n Rocamora, Gen铆s Paja, Ir谩n R. Rom谩n, Marius Miron, Xavier Serra, Juan Pablo Bello


  Access Paper or Ask Questions

Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks


Jul 22, 2021
Eduardo Fonseca, Andres Ferraro, Xavier Serra


  Access Paper or Ask Questions

LoopNet: Musical Loop Synthesis Conditioned On Intuitive Musical Parameters


May 21, 2021
Pritish Chandna, Ant贸nio Ramires, Xavier Serra, Emilia G贸mez


  Access Paper or Ask Questions

Self-Supervised Learning from Automatically Separated Sound Scenes


May 05, 2021
Eduardo Fonseca, Aren Jansen, Daniel P. W. Ellis, Scott Wisdom, Marco Tagliasacchi, John R. Hershey, Manoj Plakal, Shawn Hershey, R. Channing Moore, Xavier Serra


  Access Paper or Ask Questions

Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging


Jan 30, 2021
Andres Ferraro, Yuntae Kim, Soohyeon Lee, Biho Kim, Namjun Jo, Semi Lim, Suyon Lim, Jungtaek Jang, Sehwan Kim, Xavier Serra, Dmitry Bogdanov

* 2021 IEEE International Conference on Acoustics, Speech and Signal Processing 

  Access Paper or Ask Questions

Unsupervised Contrastive Learning of Sound Event Representations


Nov 15, 2020
Eduardo Fonseca, Diego Ortego, Kevin McGuinness, Noel E. O'Connor, Xavier Serra

* A 4-page version is submitted to ICASSP 2021 

  Access Paper or Ask Questions

Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags


Oct 27, 2020
Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra

* 5 pages, 1 figure 

  Access Paper or Ask Questions

FSD50K: an Open Dataset of Human-Labeled Sound Events


Oct 01, 2020
Eduardo Fonseca, Xavier Favory, Jordi Pons, Frederic Font, Xavier Serra


  Access Paper or Ask Questions

COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations


Jul 08, 2020
Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra

* 8 pages, 1 figure, workshop on Self-supervision in Audio and Speech at the 37th International Conference on Machine Learning (ICML), 2020, Vienna, Austria 

  Access Paper or Ask Questions

Addressing Missing Labels in Large-scale Sound Event Recognition using a Teacher-student Framework with Loss Masking


May 02, 2020
Eduardo Fonseca, Shawn Hershey, Manoj Plakal, Daniel P. W. Ellis, Aren Jansen, R. Channing Moore, Xavier Serra


  Access Paper or Ask Questions

Search Result Clustering in Collaborative Sound Collections


Apr 08, 2020
Xavier Favory, Frederic Font, Xavier Serra

* Proceedings of the 2020 International Conference on Multimedia Retrieval (ICMR 20), June 8-11, 2020, Dublin, Ireland. ACM, NewYork, NY, USA, 8 pages. https://doi.org/10.1145/3372278.3390691 
* 8 pages, 4 figures, ACM ICMR 20 

  Access Paper or Ask Questions

TensorFlow Audio Models in Essentia


Mar 16, 2020
Pablo Alonso-Jim茅nez, Dmitry Bogdanov, Jordi Pons, Xavier Serra


  Access Paper or Ask Questions

Neural Percussive Synthesis Parameterised by High-Level Timbral Features


Nov 25, 2019
Ant贸nio Ramires, Pritish Chandna, Xavier Favory, Emilia G贸mez, Xavier Serra


  Access Paper or Ask Questions

Model-agnostic Approaches to Handling Noisy Labels When Training Sound Event Classifiers


Oct 26, 2019
Eduardo Fonseca, Frederic Font, Xavier Serra

* WASPAA 2019 

  Access Paper or Ask Questions

musicnn: Pre-trained convolutional neural networks for music audio tagging


Sep 14, 2019
Jordi Pons, Xavier Serra

* Accepted to be presented at the Late-Breaking/Demo session of ISMIR 2019 

  Access Paper or Ask Questions

A hybrid parametric-deep learning approach for sound event localization and detection


Aug 27, 2019
Andres Perez-Lopez, Eduardo Fonseca, Xavier Serra

* 5 pages, 5 figures, submitted to DCASE2019 Workshop 

  Access Paper or Ask Questions

Audio tagging with noisy labels and minimal supervision


Jul 14, 2019
Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis, Xavier Serra

* submitted to DCASE2019 Workshop 

  Access Paper or Ask Questions

Toward Interpretable Music Tagging with Self-Attention


Jun 12, 2019
Minz Won, Sanghyuk Chun, Xavier Serra

* 13 pages, 12 figures; code: https://github.com/minzwon/self-attention-music-tagging 

  Access Paper or Ask Questions

Learning Sound Event Classifiers from Web Audio with Noisy Labels


Jan 04, 2019
Eduardo Fonseca, Manoj Plakal, Daniel P. W. Ellis, Frederic Font, Xavier Favory, Xavier Serra


  Access Paper or Ask Questions

Facilitating the Manual Annotation of Sounds When Using Large Taxonomies


Nov 21, 2018
Xavier Favory, Eduardo Fonseca, Frederic Font, Xavier Serra

* Proceedings of the 23rd Conference of Open Innovations Association FRUCT, Bologna, Italy. 2018. ISSN 2305-7254, ISBN 978-952-68653-6-2, FRUCT Oy, e-ISSN 2343-0737 (license CC BY-ND) 
* 5 pages, 5 figures, IEEE FRUCT International Workshop on Semantic Audio and the Internet of Things 

  Access Paper or Ask Questions

Training neural audio classifiers with few data


Nov 03, 2018
Jordi Pons, Joan Serr脿, Xavier Serra

* Code: https://github.com/jordipons/neural-classifiers-with-few-audio/ 

  Access Paper or Ask Questions

End-to-end music source separation: is it possible in the waveform domain?


Oct 29, 2018
Francesc Llu铆s, Jordi Pons, Xavier Serra

* Code: https://github.com/francesclluis/source-separation-wavenet and Demo: http://jordipons.me/apps/end-to-end-music-source-separation/ 

  Access Paper or Ask Questions

General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline


Oct 07, 2018
Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis, Xavier Favory, Jordi Pons, Xavier Serra

* Camera ready for DCASE Workshop 2018 

  Access Paper or Ask Questions