Gabriel Meseguer-Brocal

Orcid: 0000-0002-5232-8628

According to our database1, Gabriel Meseguer-Brocal authored at least 16 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
From Real to Cloned Singer Identification.
CoRR, 2024

STONE: Self-supervised Tonality Estimator.
CoRR, 2024

Detecting Synthetic Lyrics with Few-Shot Inference.
CoRR, 2024

Detecting music deepfakes is easy but actually hard.
CoRR, 2024

An Experimental Comparison of Multi-View Self-Supervised Methods for Music Tagging.
Proceedings of the IEEE International Conference on Acoustics, 2024

2022
Lyrics segmentation via bimodal text-audio representation.
Nat. Lang. Eng., 2022

Movement Analysis and Decomposition with the Continuous Wavelet Transform.
Proceedings of the MOCO '22: 8th International Conference on Movement and Computing, Chicago, IL, USA, June 22, 2022

A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
vocadito: A dataset of solo vocals with f<sub>0</sub>, note, and lyric annotations.
CoRR, 2021

MULTIMODAL ANALYSIS: Informed content estimation and audio source separation.
CoRR, 2021

2020
MULTIMODAL ANALYSIS: Informed content estimation and audio source separation. (ANALYSE MULTIMODALE: estimation informée du contenu et séparation des sources audio).
PhD thesis, 2020

Creating DALI, a Large Dataset of Synchronized Audio, Lyrics, and Notes.
Trans. Int. Soc. Music. Inf. Retr., 2020

Data Cleansing with Contrastive Learning for Vocal Note Event Annotations.
Proceedings of the 21th International Society for Music Information Retrieval Conference, 2020

Content based singing voice source separation via strong conditioning using aligned phonemes.
Proceedings of the 21th International Society for Music Information Retrieval Conference, 2020

2019
Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations.
Proceedings of the 20th International Society for Music Information Retrieval Conference, 2019

2018
DALI: A Large Dataset of Synchronized Audio, Lyrics and notes, Automatically Created using Teacher-student Machine Learning Paradigm..
Proceedings of the 19th International Society for Music Information Retrieval Conference, 2018


  Loading...