activity
20192026
most citedContent based singing voice source separation via strong conditioning using aligned phonemes

6 citations · 16 across the 18 of their papers we have counts for

collaborators

23 papers

cs.SD2026

CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations

Gabriel Meseguer-Brocal, Yuexuan Kong, Romain Hennequin

Joint-Embedding Predictive Architecture (JEPA) has shown strong performance in learning rich representations through self-supervised prediction in latent space. However, it typical…

cs.SD2026

Detection of AI-generated stems within hybrid human-AI music

François Rigaud, Gabriel Meseguer-Brocal, Benjamin Martin +1

This paper presents, to the best of our knowledge, the first study on detecting human-AI hybrid music tracks created by mixing human-produced and AI-generated stems. Building on re…

cs.LG2026

Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path

Thomas Sesmat, Gabriel Meseguer-Brocal, Geoffroy Peeters

Understanding memorization in generative models remains challenging, with implications for copyright and privacy. Beyond verbatim reproduction, models can encode subtler traces of…

cs.SD2025

Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization

Bernardo Torres, Manuel Moussallam, Gabriel Meseguer-Brocal

Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introdu…

cs.IR20251 cited

"Beyond the past": Leveraging Audio and Human Memory for Sequential Music Recommendation

Viet-Anh Tran, Bruno Sguerra, Gabriel Meseguer-Brocal +2

On music streaming services, listening sessions are often composed of a balance of familiar and new tracks. Recently, sequential recommender systems have adopted cognitive-informed…

cs.SD2025

Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval

Yuexuan Kong, Vincent Lostanlen, Romain Hennequin +2

Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retri…