Mathieu Fontaine

Mathieu Fontaine

Auto-generated profile, based on publicly available information

Mathieu Fontaine

Laboratoire de Traitement et Communication de lInformation (LTCI), Tlcom Paris, Institut Polytechnique de Paris, Palaiseau, France

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 August 2021 in IEEE Signal Processing Letters
Verified
Journal Article
Open access
YBYoshiaki Bando
Yoshiaki Bando
KSKouhei Sekiguchi
Kouhei Sekiguchi
YMYoshiki Masuyama
Yoshiki Masuyama
ANAditya Arie Nugraha
Aditya Arie Nugraha
MFMathieu Fontaine
Mathieu Fontaine
KYKazuyoshi Yoshii
Kazuyoshi Yoshii
This paper describes aneural blind source separation (BSS) method based on amortized variational inference (AVI) of a non-linear generative model of mixture signals. A classical statistical approach to BSS is to fit a linear generative model that consists of spatial and source models representing the inter-channel covariances and power spectral densities of sources, respectively. Although the variational autoencoder (VAE) has successfully been used as a non-linear source model with latent features, it should be pretrained from a sufficient amount of isolated signals. Our method, in contrast, enables the VAE-based source model to be trained only from mixture signals. Specifically, we introduce a neural mixture-to-feature inference model that directly infers the latent features from the observed mixture and integrate it with a neural feature-to-mixture generative model consisting of a full-rank spatial model and a VAE-based source model. All the models are optimized jointly such that the likelihood for the training mixtures is maximized in the framework of AVI. Once the inference model is optimized, it can be used for estimating the latent features of sources included in unseen mixture signals. The experimental results show that the proposed method outperformed the state-of-the-art BSS methods based on linear generative models and was comparable to a method based on supervised learning of the VAE-based sourcemodel.

24 November 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Open access
ANAditya Arie Nugraha
Aditya Arie Nugraha
KSKouhei Sekiguchi
Kouhei Sekiguchi
MFMathieu Fontaine
Mathieu Fontaine
YBYoshiaki Bando
Yoshiaki Bando
KYKazuyoshi Yoshii
Kazuyoshi Yoshii
This letter describes a time-varying extension of independent vector analysis (IVA) based on the normalizing flow (NF), called NF-IVA, for determined blind source separation of multichannel audio signals. As in IVA, NF-IVA estimates demixing matrices that transform mixture spectra to source spectra in the complex-valued spatial domain such that the likelihood of those matrices for the mixture spectra is maximized under some non-Gaussian source model. While IVA performs a time-invariant bijective linear transformation, NF-IVA performs a series of time-varying bijective linear transformations (flow blocks) adaptively predicted by neural networks. To regularize such transformations, we introduce a soft volume-preserving (VP) constraint. Given mixture spectra, the parameters of NF-IVA are optimized by gradient descent with backpropagation in an unsupervised manner. Experimental results show that NF-IVA successfully performs speech separation in reverberant environments with different numbers of speakers and microphones and that NF-IVA with the VP constraint outperforms NF-IVA without it, standard IVA with iterative projection, and improved IVA with gradient descent.

18 April 2013 in RAIRO - Operations Research
Verified
Journal Article
Open access
PDF file
MFMathieu Fontaine
Mathieu Fontaine
SLSamir LOUDNI
Samir LOUDNI
PBPatrice Boizumault
Patrice Boizumault
Tree decomposition introduced by Robertson and Seymour aims to decompose a problem into clusters constituting an acyclic graph. There are works exploiting tree decomposition for complete search methods. In this paper, we show how tree decomposition can be used to efficiently guide local search methods that use large neighborhoods like VNS. We propose DGVNS (Decomposition Guided VNS) which uses the graph of clusters in order to build neighborhood structures enabling better diversification and intensification. Second, we introduce tightness dependent tree decomposition which allows to take advantage of both the structure of the problem and the constraints tightness. Third, experiments performed on random instances (GRAPH) and real life instances (CELAR, SPOT5 and tagSNP) show the appropriateness and the efficiency of our approach. Moreover, we study and discuss the influence of the width of the tree decomposition on our approach and the relevance of removing clusters with very few proper variables from the tree decomposition.

5 May 2022 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
MFMathieu Fontaine
Mathieu Fontaine
KSKouhei Sekiguchi
Kouhei Sekiguchi
ANAditya Arie Nugraha
Aditya Arie Nugraha
YBYoshiaki Bando
Yoshiaki Bando
KYKazuyoshi Yoshii
Kazuyoshi Yoshii
This paper describes heavy-tailed extensions of a state-of-the-art versatile blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) from a unified point of view. The common way of deriving such an extension is to replace the multivariate complex Gaussian distribution in the likelihood function with its heavy-tailed generalization, e.g. , the multivariate complex Student’s $t$ and leptokurtic generalized Gaussian distributions, and tailor-make the corresponding parameter optimization algorithm. Using a wider class of heavy-tailed distributions called a Gaussian scale mixture (GSM), i.e. , a mixture of Gaussian distributions whose variances are perturbed by positive random scalars called impulse variables, we propose GSM-FastMNMF and develop an expectation-maximization algorithm that works even when the probability density function of the impulse variables have no analytical expressions. We show that existing heavy-tailed FastMNMF extensions are instances of GSM-FastMNMF and derive a new instance based on the generalized hyperbolic distribution that include the normal-inverse Gaussian, Student’s $t$ , and Gaussian distributions as the special cases. Our experiments show that the normal-inverse Gaussian FastMNMF outperforms the state-of-the-art FastMNMF extensions and ILRMA model in speech enhancement and separation in terms of the signal-to-distortion ratio.

13 July 2022 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
KSKouhei Sekiguchi
Kouhei Sekiguchi
YBYoshiaki Bando
Yoshiaki Bando
ANAditya Arie Nugraha
Aditya Arie Nugraha
MFMathieu Fontaine
Mathieu Fontaine
KYKazuyoshi Yoshii
Kazuyoshi Yoshii
TKTatsuya Kawahara
Tatsuya Kawahara
This article describes a computationally-efficient statistical approach to joint (semi-)blind source separation and dereverberation for multichannel noisy reverberant mixture signals. A standard approach to source separation is to formulate a generative model of a multichannel mixture spectrogram that consists of source and spatial models representing the time-frequency power spectral densities (PSDs) and spatial covariance matrices (SCMs) of source images, respectively, and find the maximum-likelihood estimates of these parameters. A state-of-the-art blind source separation method in this thread of research is fast multichannel nonnegative matrix factorization (FastMNMF) based on the low-rank PSDs and jointly-diagonalizable full-rank SCMs. To perform mutually-dependent separation and dereverberation jointly, in this paper we integrate both moving average (MA) and autoregressive (AR) models that represent the early reflections and late reverberations of sources, respectively, into the FastMNMF formalism. Using a pretrained deep generative model of speech PSDs as a source model, we realize semi-blind joint speech separation and dereverberation. We derive an iterative optimization algorithm based on iterative projection or iterative source steering for jointly and efficiently updating the AR parameters and the SCMs. Our experimental results showed the superiority of the proposed ARMA extension over its AR- or MA-ablated version in a speech separation and/or dereverberation task.

23 October 2022
Verified
Conference Paper
Open access
KSKouhei Sekiguchi
Kouhei Sekiguchi
ANAditya Arie Nugraha
Aditya Arie Nugraha
YDYicheng Du
Yicheng Du
YBYoshiaki Bando
Yoshiaki Bando
MFMathieu Fontaine
Mathieu Fontaine
KYKazuyoshi Yoshii
Kazuyoshi Yoshii
This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e.g., cocktail party). One may use a state-of-the-art blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) that works well in various environments thanks to its unsupervised nature. Its heavy computational cost, however, prevents its application to real-time processing. In contrast, a supervised beamforming method that uses a deep neural network (DNN) for estimating spatial information of speech and noise readily fits real-time processing, but suffers from drastic performance degradation in mismatched conditions. Given such complementary characteristics, we propose a dual-process robust online speech enhancement method based on DNN-based beamforming with FastMNMF-guided adaptation. FastMNMF (back end) is performed in a mini-batch style and the noisy and enhanced speech pairs are used together with the original parallel training data for updating the direction-aware DNN (front end) with backpropagation at a computationally-allowable interval. This method is used with a blind dereverberation method called weighted prediction error (WPE) for transcribing the noisy reverberant speech of a speaker, which can be detected from video or selected by a user's hand gesture or eye gaze, in a streaming manner and spatially showing the transcriptions with an AR technique. Our experiment showed that the word error rate was improved by more than 10 points with the run-time adaptation using only twelve minutes observation.