116 citations · 158 across the 9 of their papers we have counts for
12 papers
Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity
Pablo Alonso-Jiménez, Xavier Favory, Hadrien Foroughmand +4
In this work, we investigate an approach that relies on contrastive learning and music metadata as a weak source of supervision to train music representation models. Recent studies…
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…
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…
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…
FSD50K: An Open Dataset of Human-Labeled Sound Events
Eduardo Fonseca, Xavier Favory, Jordi Pons +2
Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on over 2M tracks from YouTube videos an…
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…
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…
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…
Multi Web Audio Sequencer: Collaborative Music Making
Xavier Favory, Xavier Serra
Recent advancements in web-based audio systems have enabled sufficiently accurate timing control and real-time sound processing capabilities. Numerous specialized music tools, as w…
Learning Sound Event Classifiers from Web Audio with Noisy Labels
Eduardo Fonseca, Manoj Plakal, Daniel P. W. Ellis +3
As sound event classification moves towards larger datasets, issues of label noise become inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but…
Facilitating the Manual Annotation of Sounds When Using Large Taxonomies
Xavier Favory, Eduardo Fonseca, Frederic Font +1
Properly annotated multimedia content is crucial for supporting advances in many Information Retrieval applications. It enables, for instance, the development of automatic tools fo…
General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline
Eduardo Fonseca, Manoj Plakal, Frederic Font +4
This paper describes Task 2 of the DCASE 2018 Challenge, titled "General-purpose audio tagging of Freesound content with AudioSet labels". This task was hosted on the Kaggle platfo…