Mathieu Lagrange
Publications
Publications
|
|
SCRAPL: Scattering Transform with Random Paths for Machine LearningInternational Conference on Learning Representations (ICLR), Apr 2026, Rio de Janeiro, Brazil. ⟨10.48550/arXiv.2602.11145⟩ |
|
|
Residual Hybrid FilterbanksIEEE Statistical Signal Processing Workshop (SSP), Jun 2025, Edinburgh, United Kingdom |
|
|
Bioacoustics on Tiny Hardware at the BioDCASE 2025 ChallengeDetection and Classification of Acoustic Scenes and Events (DCASE), Oct 2025, Barcelona, Spain |
|
|
S-KEY: Self-Supervised Learning of Major and Minor Keys from AudioIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2025, Hyderabad, India |
|
|
Multi-Class-Token Transformer for Multitask Self-supervised Music Information RetrievalIEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2025, Tahoe City, CA, United States |
|
|
STOMP! Self-supervised beat induction by matching pulsesInternational Society for Music Information Retrieval Late-Breaking/Demo (ISMIR-LBD), Sep 2025, Daejeon, South Korea |
|
|
GuqinSonGest: A multimodal and historically grounded dataset of guqin playing techniquesSound and Music Computing Conference (SMC), Jul 2025, Graz, Austria |
|
|
Emergent musical properties of a transformer under contrastive self-supervised learningProceedings of the International Society on Music Information Retrieval (ISMIR) Conference, Sep 2025, Daejeon, South Korea |
|
|
Characterizing new modalities of shared offices: A diary-interview methodology to inform audio augmented reality approaches11th Convention of the European Acoustics Association, Jun 2025, Málaga, Spain. pp.4925-4932, ⟨10.61782/fa.2025.0199⟩ |
|
|
Gradient Clipping Improves Neural Network Optimization for Perceptual Sound MatchingEuropean Signal Processing Conference (EUSIPCO), Sep 2025, Palermo, Italy |
|
|
Taking Advantage of Emergent Properties of a Transformer for Music Representation LearningDigital Music Research Network (DMRN), Dec 2025, Londres, United Kingdom |
|
|
Phoneme-Level Speech Intelligibility ReductionEUSIPCO 2025 - 33rd European Signal Processing Conference, Sep 2025, Palerme, Italy |
|
|
Diffusion-based spectral super-resolution of third octave acoustic sensor data: is privacy at risk ?33rd European Signal Processing Conference (EUSIPCO 2025), European Association for Signal Processing (EURASIP), Sep 2025, Palerme, Italy. pp.306 |
Nouvelle approche de réalité augmentée sonore pour le traitement du bruit en environnement intérieur : une expérience exploratoireCFA 2025 - 17e Congrès Français d'Acoustique, Apr 2025, Paris, France |
|
|
|
EMVD dataset: a dataset of extreme vocal distortion techniques used in heavy metal21st International Conference on Content-based Multimedia Indexing (CBMI 2024), Sep 2024, Reykjavik, Iceland |
|
|
Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio GenerationAudioImagination Workshop @ Neurips, Neurips, 2024, Vancouver (BC), France |
|
|
STONE: Self-supervised Tonality EstimatorInternational Society for Music Information Retrieval Conference (ISMIR), Nov 2024, San Francisco, United States |
|
|
Correlation of Fréchet Audio Distance With Human Perception of Environmental Audio Is Embedding DependentEUSIPCO, 2024, Lyon, France |
|
|
On the Robustness of Musical Timbre Perception Models: From Perceptual to Learned Approaches32th European Signal Processing Conference (EUSIPCO), Aug 2024, Lyon, France |
|
|
Towards multisensory control of physical modeling synthesisInternational Congress & Exposition on Noise Control Engineering (Inter-Noise), Aug 2024, Nantes, France |
|
|
Detection of Deepfake Environmental AudioEUSIPCO, 2024, Lyon, France |
|
|
Towards better visualizations of urban sound environments: insights from interviewsINTERNOISE 2024, Aug 2024, Nantes, France. pp.4750-4760, ⟨10.3397/IN_2024_3502⟩ |
|
|
Foley sound synthesis at the DCASE 2023 challenge2023 Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023), Sep 2023, Tampere, Finland |
|
|
Forecasting axial offset using tree-based models: a step towards improved nuclear power plants manoeuvrabilityInternational Conference on Mathematics and Computational Methods Applied to Nuclear Science and Engineering, Aug 2023, Niagara Falls, Ontario, Canada |
|
|
Perceptual musical similarity metric learning with graph neural networksIEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2023), Oct 2023, New Paltz, NY, United States |
|
|
Fitting Auditory Filterbanks with Multiresolution Neural NetworksIEEE Workshop on Applications of Signal Processing to Acoustics and Audio (WASPAA 2023), IEEE, Oct 2023, New Paltz, NY, United States. pp.1-5, ⟨10.1109/WASPAA58266.2023.10248131⟩ |
|
|
Perceptual–Neural–Physical Sound MatchingProceedings of the International Conference on Acoustics, Speech, and Signal Processing, Jun 2023, Rhodes Island, Greece, France. pp.1-5, ⟨10.1109/ICASSP49357.2023.10095391⟩ |
|
|
Spectral trancoder : using pretrained urban sound classifiers on undersampled spectral representations8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), Sep 2023, Tampere & online, Finland |
|
|
Explainable Audio Classification of Playing Techniques with Layer-wise Relevance Propagation2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Jun 2023, Rhodes, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10095894⟩ |
|
|
Differentiable Time-Frequency Scattering On GPUDigital Audio Effects Conference (DAFx), Sep 2022, Vienna, Austria |
Conception interactive en design sonore – Réduction d’un espace de design appliquée aux sons d’usage du véhicule autonome16ème Congrès Français d'Acoustique, CFA2022, Société Française d'Acoustique; Laboratoire de Mécanique et d'Acoustique, Apr 2022, Marseille, France |
|
|
|
Exploring Eco-Acoustic Data with K-Determinantal Point ProcessesDCASE 2022 - International Workshop on Detection and Classification of Acoustic Scenes and Events, 2022, Nancy, France |
|
|
Energy Efficiency is Not Enough: Towards a Batteryless Internet of SoundsProceedings of the International Workshop on the Internet of Sounds (IWIS), Audio Mostly, Sep 2021, Trento, Italy |
Multidimensional analysis to monitor the effects of COVID-19 lockdown on the urban sound environment of LorientEuropean Congress on Noise Control Engineering (EuroNoise), Oct 2021, Madeira, Portugal |
|
|
|
A high density network of low cost acoustic sensors based on wired and airborne transmission of spectral dataEuronoise 2021, Oct 2021, Madeira (on line), Portugal |
|
|
Extracting Design Recommendations from Interactive Genetic Algorithm Experiments: Application to the Design of Sounds for Electric VehiclesICED21 - 23rd International Conference on Engineering Design, Aug 2021, Gothenburg, Sweden |
|
|
Urban sensor network for characterizing the sound environment in Lorient (France) through an automatic assessment of traffic, voice and bird presence ratiosEuropean Congress on Noise Control Engineering (EuroNoise), Oct 2021, Madeira (on line), Portugal |
|
|
Bandwidth extension of musical audio signals with no side information using dilated convolutional neural networksIEEE ICASSP, May 2020, Barcelona, Spain. ⟨10.1109/icassp40776.2020.9054194⟩ |
|
|
Low-cost sensors for noise monitoring networks: a reviewForum Acusticum, Dec 2020, Lyon, France. pp.669-676, ⟨10.48465/fa.2020.0747⟩ |
|
|
Privacy aware acoustic scene synthesis using deep spectral feature inversionIEEE ICASSP, May 2020, Barcelona, Spain. ⟨10.1109/ICASSP40776.2020.9053172⟩ |
|
|
Study of the Non-negative Matrix Factorization behavior to estimate the urban traffic sound levelsICSV'26, 26th International Congress on Sound and Vibration, Jul 2019, Montreal, Canada |
|
|
Optimization of the sound of electric vehicles according to unpleasantness and detectabilityInternational Conference on Engineering Design ICED 2019, Aug 2019, DELFT, Netherlands. ⟨10.1017/dsi.2019.402⟩ |
|
|
Extended playing techniques: The next milestone in musical instrument recognition5th International Conference on Digital Libraries for Musicology, Sep 2018, Paris, France |
|
|
Visualization of audio data using stacked graphs19th International Society for Music Information Retrieval Conference, Sep 2018, Paris, France |
|
|
Estimation du niveau sonore du trafic routier au sein de mixtures sonores urbaines par la Factorisation en Matrices Non négatives14ème congrès français d'acoustique, CFA'18, Apr 2018, LE HAVRE, France |
|
|
Towards perceptual soundscape characterization using event detection algorithmsDCASE 2018, Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2018, Surrey, United Kingdom. pp.1-6 |
Characterization of urban sound environments using a comprehensive approach combining open data, measurements, and modelingAcoustics '17, Jun 2017, BOSTON, United States. 4 p, ⟨10.1121/1.4988416⟩ |
|
|
|
Creation of a corpus of realistic urban sound scenes with controlled acoustic properties173rd Meeting of the Acoustical Society of America and the 8th Forum Acusticum (Acoustics'17), Jun 2017, Boston, MA, United States. pp.1266-1277, ⟨10.1121/2.0000664⟩ |
|
|
Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task ResultsIEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2017), Sep 2017, Mohonk, United States. ⟨10.1109/waspaa.2017.8169985⟩ |
|
|
Computational experiments in Science: Horse wrangling in the digital ageResearch workshop on “Horses” in Applied Machine Learning, Oct 2016, London, United Kingdom. ⟨10.1109/TMM.2014.2330697⟩ |
|
|
Estimating traffic noise levels using acoustic monitoring: a preliminary studyDCASE 2016, Detection and Classification of Acoustic Scenes and Events, Sep 2016, BUDAPEST, Hungary. 4p |
|
|
Detection of Overlapping Acoustic Events using a Temporally-Constrained Probabilistic ModelICASSP, Mar 2016, Shanghai, China |
|
|
Classification of rainfall radar images using the scattering transformEUSIPCO, Aug 2015, Nice, France. ⟨10.1109/EUSIPCO.2015.7362722⟩ |
|
|
SimScene : a web-based acoustic scenes simulator1st Web Audio Conference (WAC), IRCAM & Mozilla, Jan 2015, Paris, France |
|
|
Alternate Level Clustering for Drum TranscriptionEUSIPCO, Sep 2015, Nice, France |
|
|
On automatic drum transcription using non-negative matrix deconvolution and itakura saito divergenceIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), Apr 2015, Brisbane, Australia. pp.414 - 418, ⟨10.1109/ICASSP.2015.7178002⟩ |
|
|
A New Experimental Approach for Urban Soundscape Characterization Based on Sound Manipulation : A Pilot StudyInternational Symposium on Musical Acoustics, Jul 2014, Le Mans, France |
|
|
A Database and Challenge for Acoustic Scene !classification and Event DetectionEUSIPCO, Sep 2013, Marrakech, Morocco |
|
|
Saliency-based modeling of acoustic scenes using sparse non-negative matrix factorizationWorkshop on Image and Audio Analysis for Multimedia Interactive, Jul 2013, Paris, France |
|
|
Exploring new features for music classificationWIAMIS, Jul 2013, Paris, France. ⟨10.1109/WIAMIS.2013.6616154⟩ |
|
|
Representing environmental sounds using the separable scattering transformICASSP, May 2013, Vancouver, Canada. ⟨10.1109/ICASSP.2013.6639358⟩ |
|
|
Detection and classification of acoustic scenes and events: An IEEE AASP challengeIEEE WASPAA, Oct 2013, New Paltz, United States. ⟨10.1109/WASPAA.2013.6701819⟩ |
Etiquetage automatique de l'audio : une approche de boosting régressif basée sur une fusion souple d'annotateursCoresa, 2013, NA, France |
|
|
|
Sparse representations for modeling environmental acoustic scenes, application to train stations soundscapesAcoustics 2012, Apr 2012, Nantes, France |
|
|
Cluster aware normalization for enhancing audio similarityIEEE ICASSP, Jan 2012, Las Vegas, United States |
|
|
A regressive boosting approach to automatic audio tagging based on soft annotator fusionIEEE ICASSP, Mar 2012, Kyoto, Japan. ⟨10.1109/ICASSP.2012.6287820⟩ |
|
|
Robust singer identification in polyphonic music using melody enhancement and uncertainty-based learning13th International Society for Music Information Retrieval Conference (ISMIR), Oct 2012, Porto, Portugal |
|
|
Characterisation of Acoustic Scenes using a Temporally Constrained Shit-Invariant ModelDAFx, Sep 2012, York, United Kingdom |
|
|
Adaptive N-normalization for enhancing music similarityIEEE ICASSP, May 2011, Prague, Czech Republic. ⟨10.1109/ICASSP.2011.5946422⟩ |
Multi-scale temporal fusion by boosting for music classificationISMIR, 2011, Miami, United States. pp.663-668 |
|
|
|
GMM-based classification from noisy featuresInternational Workshop on Machine Listening in Multisource Environments (CHiME 2011), Sep 2011, Florence, Italy |
Drum Extraction From Polyphonic Music Based on a Spectro-Temporal Model of Percussive SoundsProc. of ICASSP, 2011, Prague, République tchèque. pp.381-384 |
|
|
|
Multimodal similarity between musical streams for cover version detectionIEEE ICASSP, Mar 2010, Dallas, United States. ⟨10.1109/ICASSP.2010.5495217⟩ |
|
|
Robust similarity metrics between audio signals based on asymmetrical spectral envelope matchingProc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2010, Dallas, Texas, United States. pp.405--408 |
|
|
Unsupervised accuracy improvement for cover song detection using Spectral Connectivity NetworkInternational Conference on Music Information Retrieval, 2010, Utrecht, Netherlands. pp.1-1 |
|
|
The DESAM toolbox: spectral analysis of musical audioInternational Conference on Digital Audio Effects (DAFx), Sep 2010, Graz, Austria. pp.254-261 |
|
|
Meter Class Profiles for Music Similarity and RetrievalInternational Society for Music Information Retrieval Conference (ISMIR), Oct 2009, Kobe, Japan |
|
|
Interoperability And The Marsyas 0.2 RuntimeICMC, 2008, Belfast, Ireland |
|
|
Time-Domain Analysis / Synthesis Of The Excitation Signal In A Source / Filter Model Of Contact SoundsICAD, 2008, Paris, France |
|
|
A Computationally Efficient Scheme for Dominant Harmonic Source SeparationICASSP, IEEE, 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4517572⟩ |
|
|
MarsyasX : Multimédia Datflow Processing vith Implicit PatchingProceeding of the 16th ACM international conference, Oct 2008, Vancouver, France. ⟨10.1145/1459359.1459510⟩ |
|
|
Two-Step Modal Identification For Increased Resolution Analysis Of Percussive SoundsDAFX, 2008, Espoo, Finland |
|
|
On The Control Of The Phase Of Resonant Filters With Applications To Percussive Sound ModellingDAFX, 2008, Espoo, Finland |
|
|
Perceptual Evaluation of a Real-time Synthesis Technique for Rolling SoundsConference on Enactive Interfaces, Nov 2007, Grenoble, France |
|
|
Assessing the Quality of the Extraction and Tracking of Sinusoidal Components: Towards an Evaluation MethodologyProceedings of the Digital Audio Effects (DAFx06) Conference, Sep 2006, Canada. pp.239--245 |
|
|
Temporal Constraints for Sound Source Formation using the Normalized CutNeural Information Processing systems (NIPS), workshop on Advances in Models for Acoustic Processing, 2006, Vancouver, Canada |
|
|
SCRIME Studio ReportInternational Computer Music Conference (ICMC), 2005, Spain. p. 515-518 |
Partial Tracking Based on Future Trajectories Exploration116-th Convention of the AES, May 2004, Germany |
Modeling Grouping Cues for Auditory Scene Analysis Using a Spectral Clustering FormulationIGI Global. Machine Audition: Principles, Algorithms and Systems,, 2011 |
Method For Estimating A Future Value Of The Axial Power Imbalance In A Nuclear Reactor.United States, Patent n° : US20240145106A1. 2024 |
|
|
S-KEY: Self-supervised Learning of Major and Minor Keys from Audio2025 |
|
|
A novel interface for audio based sound data mining2014 |
|
|
On the visual display of audio data using stacked graphs2014 |
|
|
Efficient Cover Song Identification using approximate nearest neighbors2013 |
|
|
Uncertainty-based learning of Gaussian mixture models from noisy data[Research Report] RR-7862, 2012 |
|
|
Modélisation Sinusoïdale des Sons PolyphoniquesAutre [cs.OH]. Université Sciences et Technologies - Bordeaux I, 2004. Français. ⟨NNT : ⟩ |
|
|
Modélisation long terme de signaux sonoresMachine Learning [stat.ML]. Université de Nantes, 2019 |