Publications

Victor Letzelter, David Perera, Cédric Rommel, Mathieu Fontaine, Slim Essid, Gaël Richard, Patrick Pérez (2024). Winner-takes-all learners are geometry-aware conditional density estimators. Proc. ICML.

Cite URL

Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard (2024). Speech dereverberation constrained on room impulse response characteristics. Proc. Interspeech.

Cite URL

Teysir Baoueb, Haocheng Liu, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard (2024). SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis. Proc. ICASSP.

Cite URL

Yoto Fujita, Aditya Arie Nugraha, Diego Di Carlo, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii (2024). Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising. Proc. APSIPA ASC.

Cite

Liam Kelley, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii (2024). RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation. Proc. Interspeech.

Cite URL

Victor Letzelter, Mathieu Fontaine, Mickaël Chen, Patrick Pérez, Slim Essid, Gaël Richard (2024). Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis. Proc. NeurIPS.

Cite URL

Elio Gruttadauria, Mathieu Fontaine, Slim Essid (2024). Online speaker diarization of meetings guided by speech separation. Proc. ICASSP.

Cite URL

Anton Emelchenkov, Mathieu Fontaine, Yves Grenier, Hervé Mahé, François Roueff (2024). Multifrequency Highly Oscillating Aperiodic Amplitude Estimation for Nonlinear Chirp Signal. Proc. EUSIPCO.

Cite URL

Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard (2024). GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model. Proc. ICASSP.

Cite URL

Thomas Serre, Mathieu Fontaine, Éric Benhaim, Geoffroy Dutour, Slim Essid (2024). A lightweight dual-stage framework for personalized speech enhancement based on DeepFilterNet2. Proc. ICASSP.

Cite URL

Aditya Arie Nugraha, Diego Di Carlo, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii (2023). Time-Domain Audio Source Separation Based on Gaussian Processes with Deep Kernel Learning. Proc. WASPAA.

Cite URL

Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii (2023). Neural steerer: Novel steering vector synthesis with a causal neural field over frequency and source positions. Proc. ICASSP.

Cite URL

Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii (2022). Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation. IEEE Trans. Audio, Speech, Lang. Process..

Cite URL

Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii (2022). Flow-based fast multichannel nonnegative matrix factorization for blind source separation. Proc. ICASSP.

Cite URL

Mathieu Fontaine, Diego Di Carlo, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii (2022). Elliptically Contoured Alpha-Stable Representation for MUSIC-Based Sound Source Localization. Proc. EUSIPCO.

PDF Cite

Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii (2022). DNN-free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online Fastmnmf. Proc. IWAENC.

Cite URL

Yicheng Du, Aditya Arie Nugraha, Kouhei Sekiguchi, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii (2022). Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments. Proc. Interspeech.

Cite URL

Kouhei Sekiguchi, Aditya Arie Nugraha, Yicheng Du, Yoshiaki Bando, Mathieu Fontaine, Kazuyoshi Yoshii (2022). Direction-aware adaptive online neural speech enhancement with an augmented reality headset in real noisy conversational environments. IEEE/RSJ Proc. Intelligent Robots and Systems (IROS).

Cite URL

Kouhei Sekiguchi, Yoshiaki Bando, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii, Tatsuya Kawahara (2022). Autoregressive Moving Average Jointly-Diagonalizable Spatial Covariance Analysis for Joint Source Separation and Dereverberation. IEEE/ACM Trans. Audio, Speech, Lang. Process..

Cite URL

Yicheng Du, Kouhei Sekiguchi, Yoshiaki Bando, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii, Tatsuya Kawahara (2021). Semi-supervised Multichannel Speech Separation Based on a Phone-and Speaker-Aware Deep Generative Model of Speech Spectrograms. Proc. EUSIPCO.

Cite URL

Yoshiaki Bando, Kouhei Sekiguchi, Yoshiki Masuyama, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii (2021). Neural full-rank spatial covariance analysis for blind source separation. IEEE Signal Process. Lett..

Cite URL

Kazuyoshi Yoshii, Kouhei Sekiguchi, Yoshiaki Bando, Mathieu Fontaine, Aditya Arie Nugraha (2021). Fast multichannel correlated tensor factorization for blind source separation. Proc. EUSIPCO.

PDF Cite

Kouhei Sekiguchi, Yoshiaki Bando, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii (2021). Autoregressive fast multichannel nonnegative matrix factorization for joint blind source separation and dereverberation. Proc. ICASSP.

PDF Cite

Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii (2021). Alpha-Stable Autoregressive Fast Multichannel Nonnegative Matrix Factorization for Joint Speech Enhancement and Dereverberation. Proc. Interspeech.

PDF Cite

Mathieu Fontaine, Kouhei Sekiguchi, Aditya Arie Nugraha, Kazuyoshi Yoshii (2020). Unsupervised Robust Speech Enhancement Based on Alpha-Stable Fast Multichannel Nonnegative Matrix Factorization. Proc. Interspeech.

PDF Cite

Mathieu Fontaine, Roland Badeau, Antoine Liutkus (2020). Separation of alpha-stable random vectors. Signal Processing.

PDF Cite

Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii (2020). Flow-based independent vector analysis for blind source separation. IEEE Signal Process. Lett..

Cite URL

Mathieu Fontaine (2019). Processus alpha-stables pour le traitement du signal.

PDF Cite

Mathieu Fontaine, Aditya Arie Nugraha, Roland Badeau, Kazuyoshi Yoshii, Antoine Liutkus (2019). Cauchy multichannel speech enhancement with a deep speech prior. Proc. EUSIPCO.

PDF Cite

Mathieu Fontaine, Fabian-Robert Stöter, Antoine Liutkus, Umut Şimşekli, Romain Serizel, Roland Badeau (2018). Multichannel audio modeling with elliptically stable tensor decomposition. LVA/ICA 2018, Guildford, UK.

PDF Cite

Mathieu Fontaine, Charles Vanwynsberghe, Antoine Liutkus, Roland Badeau (2017). Sketching for nearfield acoustic imaging of heavy-tailed sources. International Conference on Latent Variable Analysis and Signal Separation.

Cite

Mathieu Fontaine, Charles Vanwynsberghe, Antoine Liutkus, Roland Badeau (2017). Scalable source localization with multichannel alpha-stable distributions. Proc. EUSIPCO.

Cite

Mathieu Fontaine, Antoine Liutkus, Laurent Girin, Roland Badeau (2017). Explaining the parameterized Wiener filter with alpha-stable processes. Proc. WASPAA.

Cite