Mathieu Fontaine

65 papers A* 2A 8Misc 8Journal 30Unranked 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Contrastive Knowledge Distillation for Embedding Refinement in Personalized Speech Enhancement. CoRR Thomas Serre, Mathieu Fontaine, Éric Benhaim, Slim Essid
2026	J	`jnl`	SIRUP: A diffusion-based virtual upmixer of steering vectors for highly-directive spatialization with first-order ambisonics. CoRR Emilio Picard, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii
2025	Misc	`conf`	A Hybrid Model for Weakly-Supervised Speech Dereverberation. ICASSP Louis Bahrman, Mathieu Fontaine, Gaël Richard
2025	J	`jnl`	A Hybrid Model for Weakly-Supervised Speech Dereverberation. CoRR Louis Bahrman, Mathieu Fontaine, Gaël Richard
2025	Misc	`conf`	Contrastive Knowledge Distillation for Embedding Refinement in Personalized Speech Enhancement. ICASSP Thomas Serre, Mathieu Fontaine, Éric Benhaim, Slim Essid
2025	J	`jnl`	Déréverbération non-supervisée de la parole par modèle hybride. CoRR Louis Bahrman, Mathieu Fontaine, Gaël Richard
2025	J	`jnl`	GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesis. CoRR Teysir Baoueb, Xiaoyu Bie, Mathieu Fontaine, Gaël Richard
2025	J	`jnl`	Gaussian Process Regression of Steering Vectors With Physics-Aware Deep Composite Kernels for Augmented Listening. CoRR Diego Di Carlo, Shoichi Koyama, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2025	A	`conf`	MTSE: Multi-Target Speaker Extraction for Conversation Scenarios. INTERSPEECH Thomas Serre, Mathieu Fontaine, Eric Benhaim, Slim Essid
2025	J	`jnl`	Modèle physique variationnel pour l'estimation de réponses impulsionnelles de salles. CoRR Louis Lalay, Mathieu Fontaine, Roland Badeau
2025	J	`jnl`	Multiple Choice Learning of Low Rank Adapters for Language Modeling. CoRR Victor Letzelter, Hugo Malard, Mathieu Fontaine, Gaël Richard, Slim Essid, Andrei Bursuc, Patrick Pérez
2025	Misc	`conf`	O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization. ICASSP Elio Gruttadauria, Mathieu Fontaine, Jonathan Le Roux, Slim Essid
2025	J	`jnl`	O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization. CoRR Elio Gruttadauria, Mathieu Fontaine, Jonathan Le Roux, Slim Essid
2025	—	`conf`	Physically Informed Spatial Regularization for Sound Event Localization and Detection. WASPAA Haocheng Liu, Diego Di Carlo, Aditya Arie Nugraha, Kazuyoshi Yoshii, Gaël Richard, Mathieu Fontaine
2025	—	`conf`	SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer. EUSIPCO Diego Di Carlo, Mathieu Fontaine, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii
2025	J	`jnl`	SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer. CoRR Diego Di Carlo, Mathieu Fontaine, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii
2025	J	`jnl`	The silence of the weights: an investigation of structural pruning strategies for attention-based audio signal architectures. CoRR Andrea Diecidue, Carlo Alberto Barbano, Piero Fraternali, Mathieu Fontaine, Enzo Tartaglione
2025	J	`jnl`	U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model. CoRR Louis Bahrman, Mathieu Fontaine, Gaël Richard
2025	A	`conf`	Unified Variational and Physics-aware Model for Room Impulse Response Estimation. INTERSPEECH Louis Lalay, Mathieu Fontaine, Roland Badeau
2024	—	`conf`	A Lightweight Dual-Stage Framework for Personalized Speech Enhancement Based on Deepfilternet2. ICASSP Workshops Thomas Serre, Mathieu Fontaine, Éric Benhaim, Geoffroy Dutour, Slim Essid
2024	J	`jnl`	A lightweight dual-stage framework for personalized speech enhancement based on DeepFilterNet2. CoRR Thomas Serre, Mathieu Fontaine, Éric Benhaim, Geoffroy Dutour, Slim Essid
2024	Misc	`conf`	GLA-GRAD: A Griffin-Lim Extended Waveform Generation Diffusion Model. ICASSP Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
2024	J	`jnl`	GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model. CoRR Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
2024	—	`conf`	Multifrequency Highly Oscillating Aperiodic Amplitude Estimation for Nonlinear Chirp Signal. EUSIPCO Anton Emelchenkov, Mathieu Fontaine, Yves Grenier, Hervé Mahé, François Roueff
2024	—	`conf`	Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Direction. ICASSP Workshops Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2024	Misc	`conf`	Online Speaker Diarization of Meetings Guided by Speech Separation. ICASSP Elio Gruttadauria, Mathieu Fontaine, Slim Essid
2024	J	`jnl`	Online speaker diarization of meetings guided by speech separation. CoRR Elio Gruttadauria, Mathieu Fontaine, Slim Essid
2024	A	`conf`	RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation. INTERSPEECH Liam Kelley, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2024	—	`conf`	Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising. APSIPA Yoto Fujita, Aditya Arie Nugraha, Diego Di Carlo, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2024	J	`jnl`	Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising. CoRR Yoto Fujita, Aditya Arie Nugraha, Diego Di Carlo, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2024	Misc	`conf`	SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis. ICASSP Teysir Baoueb, Haocheng Liu, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
2024	J	`jnl`	SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis. CoRR Teysir Baoueb, Haocheng Liu, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
2024	A	`conf`	Speech dereverberation constrained on room impulse response characteristics. INTERSPEECH Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
2024	J	`jnl`	Speech dereverberation constrained on room impulse response characteristics. CoRR Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
2024	A*	`conf`	Winner-takes-all learners are geometry-aware conditional density estimators. ICML Victor Letzelter, David Perera, Cédric Rommel, Mathieu Fontaine, Slim Essid, Gaël Richard, Patrick Pérez
2024	J	`jnl`	Winner-takes-all learners are geometry-aware conditional density estimators. CoRR Victor Letzelter, David Perera, Cédric Rommel, Mathieu Fontaine, Slim Essid, Gaël Richard, Patrick Pérez
2023	J	`jnl`	Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions. CoRR Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2023	A*	`conf`	Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis. NeurIPS Victor Letzelter, Mathieu Fontaine, Mickaël Chen, Patrick Pérez, Slim Essid, Gaël Richard
2023	J	`jnl`	Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis. CoRR Victor Letzelter, Mathieu Fontaine, Mickaël Chen, Patrick Pérez, Slim Essid, Gaël Richard
2023	—	`conf`	Time-Domain Audio Source Separation Based on Gaussian Processes with Deep Kernel Learning. WASPAA Aditya Arie Nugraha, Diego Di Carlo, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2022	J	`jnl`	Autoregressive Moving Average Jointly-Diagonalizable Spatial Covariance Analysis for Joint Source Separation and Dereverberation. IEEE ACM Trans. Audio Speech Lang. Process. Kouhei Sekiguchi, Yoshiaki Bando, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii, Tatsuya Kawahara
2022	J	`jnl`	DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF. CoRR Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2022	—	`conf`	DNN-free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online Fastmnmf. IWAENC Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2022	A	`conf`	Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments. IROS Kouhei Sekiguchi, Aditya Arie Nugraha, Yicheng Du, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2022	J	`jnl`	Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments. CoRR Kouhei Sekiguchi, Aditya Arie Nugraha, Yicheng Du, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2022	A	`conf`	Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments. INTERSPEECH Yicheng Du, Aditya Arie Nugraha, Kouhei Sekiguchi, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2022	J	`jnl`	Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments. CoRR Yicheng Du, Aditya Arie Nugraha, Kouhei Sekiguchi, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii
2022	—	`conf`	Elliptically Contoured Alpha-Stable Representation for MUSIC-Based Sound Source Localization. EUSIPCO Mathieu Fontaine, Diego Di Carlo, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii
2022	Misc	`conf`	Flow-Based Fast Multichannel Nonnegative Matrix Factorization for Blind Source Separation. ICASSP Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2022	J	`jnl`	Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation. CoRR Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii
2022	J	`jnl`	Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation. IEEE ACM Trans. Audio Speech Lang. Process. Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii
2021	A	`conf`	Alpha-Stable Autoregressive Fast Multichannel Nonnegative Matrix Factorization for Joint Speech Enhancement and Dereverberation. Interspeech Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii
2021	Misc	`conf`	Autoregressive Fast Multichannel Nonnegative Matrix Factorization For Joint Blind Source Separation And Dereverberation. ICASSP Kouhei Sekiguchi, Yoshiaki Bando, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii
2021	J	`jnl`	Neural Full-Rank Spatial Covariance Analysis for Blind Source Separation. IEEE Signal Process. Lett. Yoshiaki Bando, Kouhei Sekiguchi, Yoshiki Masuyama, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii
2020	—	`conf`	Fast Multichannel Correlated Tensor Factorization for Blind Source Separation. EUSIPCO Kazuyoshi Yoshii, Kouhei Sekiguchi, Yoshiaki Bando, Mathieu Fontaine, Aditya Arie Nugraha
2020	J	`jnl`	Flow-Based Independent Vector Analysis for Blind Source Separation. IEEE Signal Process. Lett. Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii
2020	—	`conf`	Semi-supervised Multichannel Speech Separation Based on a Phone- and Speaker-Aware Deep Generative Model of Speech Spectrograms. EUSIPCO Yicheng Du, Kouhei Sekiguchi, Yoshiaki Bando, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii, Tatsuya Kawahara
2020	J	`jnl`	Separation of alpha-stable random vectors. Signal Process. Mathieu Fontaine, Roland Badeau, Antoine Liutkus
2020	A	`conf`	Unsupervised Robust Speech Enhancement Based on Alpha-Stable Fast Multichannel Nonnegative Matrix Factorization. INTERSPEECH Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Kazuyoshi Yoshii
2019	—	`conf`	Cauchy Multichannel Speech Enhancement with a Deep Speech Prior. EUSIPCO Mathieu Fontaine, Aditya Arie Nugraha, Roland Badeau, Kazuyoshi Yoshii, Antoine Liutkus
2019	—	`—`	Processus alpha-stables pour le traitement du signal. (Alpha-stable processes for signal processing). Mathieu Fontaine
2018	—	`conf`	Multichannel Audio Modeling with Elliptically Stable Tensor Decomposition. LVA/ICA Mathieu Fontaine, Fabian-Robert Stöter, Antoine Liutkus, Umut Simsekli, Romain Serizel, Roland Badeau
2017	—	`conf`	Explaining the parameterized wiener filter with alpha-stable processes. WASPAA Mathieu Fontaine, Antoine Liutkus, Laurent Girin, Roland Badeau
2017	—	`conf`	Scalable source localization with multichannel α-stable distributions. EUSIPCO Mathieu Fontaine, Charles Vanwynsberghe, Antoine Liutkus, Roland Badeau
2017	—	`conf`	Sketching for Nearfield Acoustic Imaging of Heavy-Tailed Sources. LVA/ICA Mathieu Fontaine, Charles Vanwynsberghe, Antoine Liutkus, Roland Badeau