17 citations · 38 across the 24 of their papers we have counts for
24 papers
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…
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…
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…
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…
"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…
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…
Emergent musical properties of a transformer under contrastive self-supervised learning
Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen +2
In music information retrieval (MIR), contrastive self-supervised learning for general-purpose representation models is effective for global tasks such as automatic tagging. Howeve…
AI-Generated Song Detection via Lyrics Transcripts
Markus Frohmann, Elena V. Epure, Gabriel Meseguer-Brocal +2
The recent rise in capabilities of AI-based music generation tools has created an upheaval in the music industry, necessitating the creation of accurate methods to detect such AI-g…
A Fourier Explanation of AI-music Artifacts
Darius Afchar, Gabriel Meseguer-Brocal, Kamil Akesbi +1
The rapid rise of generative AI has transformed music creation, with millions of users engaging in AI-generated music. Despite its popularity, concerns regarding copyright infringe…
AI-Generated Music Detection and its Challenges
Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
In the face of a new era of generative models, the detection of artificially generated content has become a matter of utmost importance. In particular, the ability to create credib…
S-KEY: Self-supervised Learning of Major and Minor Keys from Audio
Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen +2
STONE, the current method in self-supervised learning for tonality estimation in music signals, cannot distinguish relative keys, such as C major versus A minor. In this article, w…
Harnessing High-Level Song Descriptors towards Natural Language-Based Music Recommendation
Elena V. Epure, Gabriel Meseguer-Brocal, Darius Afchar +1
Recommender systems relying on Language Models (LMs) have gained popularity in assisting users to navigate large catalogs. LMs often exploit item high-level descriptors, i.e. categ…
From Real to Cloned Singer Identification
Dorian Desblancs, Gabriel Meseguer-Brocal, Romain Hennequin +1
Cloned voices of popular singers sound increasingly realistic and have gained popularity over the past few years. They however pose a threat to the industry due to personality righ…
STONE: Self-supervised Tonality Estimator
Yuexuan Kong, Vincent Lostanlen, Gabriel Meseguer-Brocal +3
Although deep neural networks can estimate the key of a musical piece, their supervision incurs a massive annotation effort. Against this shortcoming, we present STONE, the first s…
Synthetic Lyrics Detection Across Languages and Genres
Yanis Labrak, Markus Frohmann, Gabriel Meseguer-Brocal +1
In recent years, the use of large language models (LLMs) to generate music content, particularly lyrics, has gained in popularity. These advances provide valuable tools for artists…
Detecting music deepfakes is easy but actually hard
Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
In the face of a new era of generative models, the detection of artificially generated content has become a matter of utmost importance. The ability to create credible minute-long…
An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging
Gabriel Meseguer-Brocal, Dorian Desblancs, Romain Hennequin
Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the m…
A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation
Rachel M. Bittner, Juan José Bosch, David Rubinstein +2
Automatic Music Transcription (AMT) has been recognized as a key enabling technology with a wide range of applications. Given the task's complexity, best results have typically bee…
vocadito: A dataset of solo vocals with , note, and lyric annotations
Rachel M. Bittner, Katherine Pasalo, Juan José Bosch +2
To compliment the existing set of datasets, we present a small dataset entitled vocadito, consisting of 40 short excerpts of monophonic singing, sung in 7 different languages by si…
MULTIMODAL ANALYSIS: Informed content estimation and audio source separation
Gabriel Meseguer-Brocal
This dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. A…
Content based singing voice source separation via strong conditioning using aligned phonemes
Gabriel Meseguer-Brocal, Geoffroy Peeters
Informed source separation has recently gained renewed interest with the introduction of neural networks and the availability of large multitrack datasets containing both the mixtu…
Data Cleansing with Contrastive Learning for Vocal Note Event Annotations
Gabriel Meseguer-Brocal, Rachel Bittner, Simon Durand +1
Data cleansing is a well studied strategy for cleaning erroneous labels in datasets, which has not yet been widely adopted in Music Information Retrieval. Previously proposed data…
Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations
Gabriel Meseguer-Brocal, Geoffroy Peeters
Data-driven models for audio source separation such as U-Net or Wave-U-Net are usually models dedicated to and specifically trained for a single task, e.g. a particular instrument…
DALI: a large Dataset of synchronized Audio, LyrIcs and notes, automatically created using teacher-student machine learning paradigm
Gabriel Meseguer-Brocal, Alice Cohen-Hadria, Geoffroy Peeters
The goal of this paper is twofold. First, we introduce DALI, a large and rich multimodal dataset containing 5358 audio tracks with their time-aligned vocal melody notes and lyrics…