The ADASP group of Télécom-Paris is presenting 3 papers, 1 tutorial, and 1 late braking demo this week at the 25th International Society for Music Information Retrieval (ISMIR 2024) Conference.
This month’s Listen-Lab seminar will feature a brief presentation of each work (listed below), followed by ADASP group members sharing their favorite papers and key highlights from the conference.
- Morgan Buisson, Brian Mcfee, Slim Essid
Using Pairwise Link Prediction and Graph Attention Networks for Music Structure Analysis
- Antonin Gagnere, Geoffroy Peeters, Slim Essid
A Contrastive Self-Supervised Learning scheme for beat tracking amenable to few-shot learning
- Alain Riou, Stefan Lattner, Gaëtan Hadjeres, Michael Anslow, Geoffroy Peeters
Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation
- Geoffroy Peeters, Gabriel Meseguer Brocal, Alain Riou, and Stefan Lattner
Deep Learning 101 for Audio-based MIR
- Jose Gil Panal, Aurelien David, Gaël Richard
Hi-Audio online platform: opportunities and challenges of collecting varied music data on the web
Links:
