Mathieu Lagrange
YOU?
Author Swipe
View article: Extreme Metal Vocals Dataset (EMVD)
Extreme Metal Vocals Dataset (EMVD) Open
Extreme Metal Vocals Dataset (EMVD) Version 1.1, December 2025 Publication If using this data in an academic work, please reference the DOI and version, as well as cite the following paper, which presented the data collection procedure and…
View article: Bioacoustics on Tiny Hardware at the BioDCASE 2025 Challenge
Bioacoustics on Tiny Hardware at the BioDCASE 2025 Challenge Open
International audience
View article: Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval
Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval Open
Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retrieval (MIR) faces a dilemma: the former is more effective on…
View article: S-KEY: Self-supervised Learning of Major and Minor Keys from Audio
S-KEY: Self-supervised Learning of Major and Minor Keys from Audio Open
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, we extend the neural network architecture and learning objec…
View article: Sound Scene Synthesis at the DCASE 2024 Challenge
Sound Scene Synthesis at the DCASE 2024 Challenge Open
This paper presents Task 7 at the DCASE 2024 Challenge: sound scene synthesis. Recent advances in sound synthesis and generative models have enabled the creation of realistic and diverse audio content. We introduce a standardized evaluatio…
View article: Understanding Equivariant Self-Supervised Learning in Musical Pitch Class Space
Understanding Equivariant Self-Supervised Learning in Musical Pitch Class Space Open
International audience
View article: Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation Open
Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Clas…
View article: SKY: Self-supervised Learning of Major and Minor Keys from Audio
SKY: Self-supervised Learning of Major and Minor Keys from Audio Open
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, we extend the neural network architecture and learning objec…
View article: EMVD dataset: a dataset of extreme vocal distortion techniques used in heavy metal
EMVD dataset: a dataset of extreme vocal distortion techniques used in heavy metal Open
In this paper, we introduce the Extreme Metal Vocals Dataset, which comprises a collection of recordings of extreme vocal techniques performed within the realm of heavy metal music. The dataset consists of 760 audio excerpts of 1 second to…
View article: Detection of Deepfake Environmental Audio
Detection of Deepfake Environmental Audio Open
With the ever-rising quality of deep generative models, it is increasingly important to be able to discern whether the audio data at hand have been recorded or synthesized. Although the detection of fake speech signals has been studied ext…
View article: On the Robustness of Musical Timbre Perception Models: From Perceptual to Learned Approaches
On the Robustness of Musical Timbre Perception Models: From Perceptual to Learned Approaches Open
International audience
View article: STONE: Self-supervised Tonality Estimator
STONE: Self-supervised Tonality Estimator Open
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 self-supervised tonality estimator. The architecture behind …
View article: Sound source classification for soundscape analysis using fast third-octave bands data from an urban acoustic sensor network
Sound source classification for soundscape analysis using fast third-octave bands data from an urban acoustic sensor network Open
The exploration of the soundscape relies strongly on the characterization of the sound sources in the sound environment. Novel sound source classifiers, called pre-trained audio neural networks (PANNs), are capable of predicting the presen…
View article: Correlation of Fréchet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant
Correlation of Fréchet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant Open
This paper explores whether considering alternative domain-specific embeddings to calculate the Fréchet Audio Distance (FAD) metric can help the FAD to correlate better with perceptual ratings of environmental sounds. We used embeddings fr…
View article: Acoustical and behavioral heuristics for fast interactive sound design
Acoustical and behavioral heuristics for fast interactive sound design Open
During their creative process, designers routinely seek the feedback of end users. Yet, the collection of perceptual judgments is costly and time-consuming, since it involves repeated exposure to the designed object under elementary variat…
View article: Learning to Solve Inverse Problems for Perceptual Sound Matching
Learning to Solve Inverse Problems for Perceptual Sound Matching Open
International audience
View article: Lorient-1k
Lorient-1k Open
Created By Félix Gontier and Mathieu Lagrange, LS2N, CNRS, Ecole Centrale Nantes Contact : [email protected] If used for research, please refer to: @article{gontier2021training, title={Polyphonic training set synthesis improves self…
View article: Lorient-1k
Lorient-1k Open
Created By Félix Gontier and Mathieu Lagrange, LS2N, CNRS, Ecole Centrale Nantes Contact : [email protected] If used for research, please refer to: @article{gontier2021training, title={Polyphonic training set synthesis improves self…
View article: Lorient-1k
Lorient-1k Open
Created By Félix Gontier and Mathieu Lagrange, LS2N, CNRS, Ecole Centrale Nantes Contact : [email protected] If used for research, please refer to: @article{gontier2021training, title={Polyphonic training set synthesis improves self…
View article: Efficient bandwidth extension of musical signals using a differentiable harmonic plus noise model
Efficient bandwidth extension of musical signals using a differentiable harmonic plus noise model Open
The task of bandwidth extension addresses the generation of missing high frequencies of audio signals based on knowledge of the low-frequency part of the sound. This task applies to various problems, such as audio coding or audio restorati…
View article: Learning to Solve Inverse Problems for Perceptual Sound Matching
Learning to Solve Inverse Problems for Perceptual Sound Matching Open
Perceptual sound matching (PSM) aims to find the input parameters to a synthesizer so as to best imitate an audio target. Deep learning for PSM optimizes a neural network to analyze and reconstruct prerecorded samples. In this context, our…
View article: Efficient bandwidth extension of musical signals using a differentiable harmonic plus noise model
Efficient bandwidth extension of musical signals using a differentiable harmonic plus noise model Open
The task of bandwidth extension addresses the generation of missing high frequencies of audio signals based on knowledge of the low-frequency part of the sound. This task applies to various problems, such as audio coding or audio restorati…
View article: Extreme Metal Vocals Dataset (EMVD)
Extreme Metal Vocals Dataset (EMVD) Open
Extreme Metal Vocals Dataset (EMVD) Version 1.0, October 2023 Created by Modan Tailleur (1,3), Julien Pinquier (2), Laurent Millot (1), Corsin Vogel (1), Mathieu Lagrange (3) ENS Louis-Lumière, Saint-Denis, France IRIT, Université de Toulo…
View article: Mesostructures: Beyond Spectrogram Loss in Differentiable Time–Frequency Analysis
Mesostructures: Beyond Spectrogram Loss in Differentiable Time–Frequency Analysis Open
Computer musicians refer to mesostructures as the intermediate levels of articulation between the microstructure of waveshapes and the macrostructure of musical forms.Examples of mesostructures include melody, arpeggios, syncopation, polyp…
View article: Forecasting axial offset using tree-based models: a step towards improved nuclear power plants manoeuvrability
Forecasting axial offset using tree-based models: a step towards improved nuclear power plants manoeuvrability Open
International audience
View article: Fitting Auditory Filterbanks with Multiresolution Neural Networks
Fitting Auditory Filterbanks with Multiresolution Neural Networks Open
Waveform-based deep learning faces a dilemma between nonparametric and parametric approaches. On one hand, convolutional neural networks (convnets) may approximate any linear time-invariant system; yet, in practice, their frequency respons…
View article: Perceptual–Neural–Physical Sound Matching
Perceptual–Neural–Physical Sound Matching Open
International audience
View article: Explainable audio Classification of Playing Techniques with Layer-wise Relevance Propagation
Explainable audio Classification of Playing Techniques with Layer-wise Relevance Propagation Open
International audience
View article: Foley Sound Synthesis at the DCASE 2023 Challenge
Foley Sound Synthesis at the DCASE 2023 Challenge Open
The addition of Foley sound effects during post-production is a common technique used to enhance the perceived acoustic properties of multimedia content. Traditionally, Foley sound has been produced by human Foley artists, which involves m…