Yann Bayle

University of Bordeaux · LaBRI, CNRS

Vacuum tube amplifiers present sonic characteristics often coveted by musicians, that are due to the distinct distortion of their circuits and accurately modeling such effects can be a challenging task. A recent rise in machine learning has lead to the ubiquity of neural networks in all fields including virtual analog modeling. This has lead to the...

Shark populations that are distributed alongside a latitudinal gradient often display body size differences at sexual maturity and vicariance patterns related to their number of tooth files. Previous works have demonstrated that Scyliorhinus canicula populations differ between the northeastern Atlantic Ocean and the Mediterranean Sea based on biolo...

Vacuum tube amplifiers present sonic characteristics frequently coveted by musicians, that are often due to the distinct nonlinearities of their circuits, and accurately modelling such effects can be a challenging task. A recent rise in machine learning methods has lead to the ubiquity of neural networks in all fields of study including virtual ana...

The present dataset contains the 3D models analyzed in Berio, F., Bayle, Y., Baum, D., Goudemand, N., and Debiais-Thibaud, M. 2022. Hide and seek shark teeth in Random Forests: Machine learning applied to Scyliorhinus canicula. It contains the head surfaces of 56 North Atlantic and Mediterranean small-spotted catsharks Scyliorhinus canicula, from w...

Regionalization of the vertebral column occurred early during vertebrate evolution and has been extensively investigated in mammals. However, less data are available on vertebral regions of crown gnathostomes. This is particularly true for batoids (skates, sawfishes, guitarfishes, and rays) whose vertebral column has long been considered to be comp...

This paper introduces SATIN, the Set of Audio Tags and Identifiers Normalized. SATIN is a database of 400k audio-related metadata and identifiers that aims at facilitating reproducibility and comparisons among the Music Information Retrieval (MIR) algorithms. The idea is to take advantage of partnerships between scientists and private companies tha...

We introduce KaraMIR, a musical project dedicated to karaoke song analysis. Within KaraMIR, we define Kara1k, a dataset composed of 1000 cover songs provided by Recisio Karafun application, and the corresponding 1000 songs by the original artists. Kara1k is mainly dedicated toward cover song identification and singing voice analysis. For both tasks...

Ce mémoire de thèse de doctorat présente, discute et propose des outils de fouille automatique de mégadonnées dans un contexte de classification supervisée musical.L'application principale concerne la classification automatique des thèmes musicaux afin de générer des listes de lecture thématiques.Le premier chapitre introduit les différents context...

Keywords: Signal processing, Machine learning, Data augmentation, Music Information Retrieval, Autotagging

Poster from IEEE ISM 2017: Kara1k: a karaoke dataset for cover song identification and singing voice analysis. Explaining the new Kara1k dataset for cover song identification and singing voice analysis. Download below.

We introduce Kara1k, a new musical dataset com- posed of 2,000 analyzed songs thanks to a partnership with a karaoke company. The dataset is divided into 1,000 cover songs provided by Recisio Karafun application http://www.karafun.com , and the corresponding 1,000 songs by the original artists. Kara1k is mainly dedicated toward cover song identific...

Four experiments investigated change detection in acoustic scenes consisting of a sum of five amplitude-modulated pure tones. As the tones were about 0.7 octave apart and were amplitude-modulated with different frequencies (in the range 2–32 Hz), they were perceived as separate streams. Listeners had to detect a change in the frequency (experiments...

This study deals with the classification of Instrumentals and Songs in a bigger musical database than what was used in all previous studies. Songs are musical pieces containing singing voice, contrary to Instrumentals. This research tackles the imbalance between the number of Instrumentals and the numerous Songs present in industrial musical databa...

Poster presented to describe the article published in CBMI 2017.

This paper introduces SATIN, the Set of Audio Tags and Identifiers Normalized. SATIN is a database of 400k audio-related metadata and identifiers that aims at facilitating reproducibility and comparisons among the MIR algorithms. The idea is to take advantage of partnerships between scientists and private companies that host millions of tracks. Sci...

Presentation of current state-of-the-art, current progress and future work

Le chant est un élément remarquable d’une chanson et sa détection automatique au sein d’un morceau est un défi largement étudié. Cet article propose une approche permettant de discriminer les titres musicaux comportant du chant dans une base de données musicales conséquente. L’approche précédemment proposée par Ghosal et al.[9] fonde la prise de dé...