Gabriel Meseguer-Brocal

45 papers A 1Misc 4Journal 26Unranked 13

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings. ECIR (1) Joanne Affolter, Benjamin Martin, Elena V. Epure, Gabriel Meseguer-Brocal, Frédéric Kaplan
2026	J	`jnl`	Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings. CoRR Joanne Affolter, Benjamin Martin, Elena V. Epure, Gabriel Meseguer-Brocal, Frédéric Kaplan
2025	A	`conf`	"Beyond the past": Leveraging Audio and Human Memory for Sequential Music Recommendation. RecSys Viet-Anh Tran, Bruno Sguerra, Gabriel Meseguer-Brocal, Léa Briand, Manuel Moussallam
2025	J	`jnl`	"Beyond the past": Leveraging Audio and Human Memory for Sequential Music Recommendation. CoRR Viet-Anh Tran, Bruno Sguerra, Gabriel Meseguer-Brocal, Léa Briand, Manuel Moussallam
2025	—	`conf`	A Fourier Explanation of AI-music Artifacts. ISMIR Darius Afchar, Gabriel Meseguer-Brocal, Kamil Akesbi, Romain Hennequin
2025	J	`jnl`	A Fourier Explanation of AI-music Artifacts. CoRR Darius Afchar, Gabriel Meseguer-Brocal, Kamil Akesbi, Romain Hennequin
2025	Misc	`conf`	AI-Generated Music Detection and its Challenges. ICASSP Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
2025	J	`jnl`	AI-Generated Music Detection and its Challenges. CoRR Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
2025	—	`conf`	AI-Generated Song Detection via Lyrics Transcripts. ISMIR Markus Frohmann, Elena V. Epure, Gabriel Meseguer-Brocal, Markus Schedl, Romain Hennequin
2025	J	`jnl`	AI-Generated Song Detection via Lyrics Transcripts. CoRR Markus Frohmann, Elena V. Epure, Gabriel Meseguer-Brocal, Markus Schedl, Romain Hennequin
2025	—	`conf`	Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion. ACL (Findings) Markus Frohmann, Gabriel Meseguer-Brocal, Markus Schedl, Elena V. Epure
2025	J	`jnl`	Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion. CoRR Markus Frohmann, Gabriel Meseguer-Brocal, Markus Schedl, Elena V. Epure
2025	—	`conf`	Emergent musical properties of a transformer under contrastive self-supervised learning. ISMIR Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen, Mathieu Lagrange, Romain Hennequin
2025	J	`jnl`	Emergent musical properties of a transformer under contrastive self-supervised learning. CoRR Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen, Mathieu Lagrange, Romain Hennequin
2025	J	`jnl`	Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization. CoRR Bernardo Torres, Manuel Moussallam, Gabriel Meseguer-Brocal
2025	—	`conf`	Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval. WASPAA Yuexuan Kong, Vincent Lostanlen, Romain Hennequin, Mathieu Lagrange, Gabriel Meseguer-Brocal
2025	J	`jnl`	Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval. CoRR Yuexuan Kong, Vincent Lostanlen, Romain Hennequin, Mathieu Lagrange, Gabriel Meseguer-Brocal
2025	Misc	`conf`	S-KEY: Self-supervised Learning of Major and Minor Keys from Audio. ICASSP Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen, Mathieu Lagrange, Romain Hennequin
2025	J	`jnl`	S-KEY: Self-supervised Learning of Major and Minor Keys from Audio. CoRR Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen, Mathieu Lagrange, Romain Hennequin
2025	J	`jnl`	Understanding Equivariant Self-Supervised Learning in Musical Pitch Class Space. IEEE Signal Process. Lett. Vincent Lostanlen, Yuexuan Kong, Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin
2024	J	`jnl`	An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging. CoRR Gabriel Meseguer-Brocal, Dorian Desblancs, Romain Hennequin
2024	Misc	`conf`	An Experimental Comparison of Multi-View Self-Supervised Methods for Music Tagging. ICASSP Gabriel Meseguer-Brocal, Dorian Desblancs, Romain Hennequin
2024	J	`jnl`	Detecting Synthetic Lyrics with Few-Shot Inference. CoRR Yanis Labrak, Gabriel Meseguer-Brocal, Elena V. Epure
2024	J	`jnl`	Detecting music deepfakes is easy but actually hard. CoRR Darius Afchar, Gabriel Meseguer-Brocal, Romain Hennequin
2024	—	`conf`	From Real to Cloned Singer Identification. ISMIR Dorian Desblancs, Gabriel Meseguer-Brocal, Romain Hennequin, Manuel Moussallam
2024	J	`jnl`	From Real to Cloned Singer Identification. CoRR Dorian Desblancs, Gabriel Meseguer-Brocal, Romain Hennequin, Manuel Moussallam
2024	J	`jnl`	Harnessing High-Level Song Descriptors towards Natural Language-Based Music Recommendation. CoRR Elena V. Epure, Gabriel Meseguer-Brocal, Darius Afchar, Romain Hennequin
2024	—	`conf`	STONE: Self-Supervised Tonality Estimator. ISMIR Yuexuan Kong, Vincent Lostanlen, Gabriel Meseguer-Brocal, Stella Wong, Mathieu Lagrange, Romain Hennequin
2024	J	`jnl`	STONE: Self-supervised Tonality Estimator. CoRR Yuexuan Kong, Vincent Lostanlen, Gabriel Meseguer-Brocal, Stella Wong, Mathieu Lagrange, Romain Hennequin
2022	Misc	`conf`	A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation. ICASSP Rachel M. Bittner, Juan José Bosch, David Rubinstein, Gabriel Meseguer-Brocal, Sebastian Ewert
2022	J	`jnl`	A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation. CoRR Rachel M. Bittner, Juan José Bosch, David Rubinstein, Gabriel Meseguer-Brocal, Sebastian Ewert
2022	J	`jnl`	Lyrics segmentation via bimodal text-audio representation. Nat. Lang. Eng. Michael Fell, Yaroslav Nechaev, Gabriel Meseguer-Brocal, Elena Cabrio, Fabien Gandon, Geoffroy Peeters
2022	—	`conf`	Movement Analysis and Decomposition with the Continuous Wavelet Transform. MOCO Jules Françoise, Gabriel Meseguer-Brocal, Frédéric Bevilacqua
2021	J	`jnl`	MULTIMODAL ANALYSIS: Informed content estimation and audio source separation. CoRR Gabriel Meseguer-Brocal
2021	J	`jnl`	vocadito: A dataset of solo vocals with f CoRR Rachel M. Bittner, Katherine Pasalo, Juan José Bosch, Gabriel Meseguer-Brocal, David Rubinstein
2020	—	`conf`	Content based singing voice source separation via strong conditioning using aligned phonemes. ISMIR Gabriel Meseguer-Brocal, Geoffroy Peeters
2020	J	`jnl`	Content based singing voice source separation via strong conditioning using aligned phonemes. CoRR Gabriel Meseguer-Brocal, Geoffroy Peeters
2020	J	`jnl`	Creating DALI, a Large Dataset of Synchronized Audio, Lyrics, and Notes. Trans. Int. Soc. Music. Inf. Retr. Gabriel Meseguer-Brocal, Alice Cohen-Hadria, Geoffroy Peeters
2020	—	`conf`	Data Cleansing with Contrastive Learning for Vocal Note Event Annotations. ISMIR Gabriel Meseguer-Brocal, Rachel M. Bittner, Simon Durand, Brian Brost
2020	J	`jnl`	Data Cleansing with Contrastive Learning for Vocal Note Event Annotations. CoRR Gabriel Meseguer-Brocal, Rachel M. Bittner, Simon Durand, Brian Brost
2020	—	`—`	MULTIMODAL ANALYSIS: Informed content estimation and audio source separation. (ANALYSE MULTIMODALE: estimation informée du contenu et séparation des sources audio). Gabriel Meseguer-Brocal
2019	—	`conf`	Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations. ISMIR Gabriel Meseguer-Brocal, Geoffroy Peeters
2019	J	`jnl`	Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations. CoRR Gabriel Meseguer-Brocal, Geoffroy Peeters
2019	J	`jnl`	DALI: a large Dataset of synchronized Audio, LyrIcs and notes, automatically created using teacher-student machine learning paradigm. CoRR Gabriel Meseguer-Brocal, Alice Cohen-Hadria, Geoffroy Peeters
2018	—	`conf`	DALI: A Large Dataset of Synchronized Audio, Lyrics and notes, Automatically Created using Teacher-student Machine Learning Paradigm.. ISMIR Gabriel Meseguer-Brocal, Alice Cohen-Hadria, Geoffroy Peeters