activity
20182021
most citedEnriched Music Representations with Multiple Cross-modal Contrastive Learning

23 citations · 39 across the 6 of their papers we have counts for

collaborators

10 papers

cs.LG20214 cited

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

Benno Weck, Xavier Favory, Konstantinos Drossos +1

Automated audio captioning (AAC) is the task of automatically generating textual descriptions for general audio signals. A captioning system has to identify various information fro…

cs.SD202123 cited

Enriched Music Representations with Multiple Cross-modal Contrastive Learning

Andres Ferraro, Xavier Favory, Konstantinos Drossos +2

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtai…

cs.SD2020

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

Xavier Favory, Konstantinos Drossos, Tuomas Virtanen +1

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Publish…

cs.LG20209 cited

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

Xavier Favory, Konstantinos Drossos, Tuomas Virtanen +1

Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a la…

cs.IR20203 cited

Search Result Clustering in Collaborative Sound Collections

Xavier Favory, Frederic Font, Xavier Serra

The large size of nowadays' online multimedia databases makes retrieving their content a difficult and time-consuming task. Users of online sound collections typically submit searc…

eess.AS2019

Neural Percussive Synthesis Parameterised by High-Level Timbral Features

António Ramires, Pritish Chandna, Xavier Favory +2

We present a deep neural network-based methodology for synthesising percussive sounds with control over high-level timbral characteristics of the sounds. This approach allows for i…