Léo Cances

According to our database, Léo Cances authored at least 7 papers between 2018 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

Comparison of semi-supervised deep learning algorithms for audio classification.

Léo Cances, Etienne Labbé, Thomas Pellegrini

EURASIP J. Audio Speech Music. Process., 2022

2021

Apprentissage profond faiblement supervisé et semi-supervisé pour la détection d'évènements sonores. (Weakly supervised and semi-supervised deep learning for sound event detection).

Léo Cances

PhD thesis, 2021

Improving Deep-learning-based Semi-supervised Audio Tagging with Mixup.

Léo Cances, Etienne Labbé, Thomas Pellegrini

CoRR, 2021

Comparison of Deep Co-Training and Mean-Teacher Approaches for Semi-Supervised Audio Tagging.

Léo Cances, Thomas Pellegrini

Proceedings of the IEEE International Conference on Acoustics, 2021

2019

Evaluation of Post-Processing Algorithms for Polyphonic Sound Event Detection.

Léo Cances, Patrice Guyot, Thomas Pellegrini

Proceedings of the 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2019

Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection.

Thomas Pellegrini, Léo Cances

Proceedings of the International Joint Conference on Neural Networks, 2019

2018

Sound event detection from weak annotations: weighted-GRU versus multi-instance-learning.

Léo Cances, Thomas Pellegrini, Patrice Guyot

Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events, 2018