Dominique Fourer

Quentin Legros, Dominique Fourer, Sylvain Meignen et al.

This paper addresses the problem of estimating the modes of an observed non-stationary mixture signal in the presence of an arbitrary distributed noise. A novel Bayesian model is introduced to estimate the model parameters from the spectrogram of the observed signal, by resorting to the stochastic version of the EM algorithm to avoid the computationally expensive joint parameters estimation from the posterior distribution. The proposed method is assessed through comparative experiments with state-of-the-art methods. The obtained results validate the proposed approach by highlighting an improvement of the modes estimation performance.

Ahmad Fall, Federica Granese, Alex Lence et al.

Monitoring and analyzing electrocardiogram (ECG) signals, even under varying physiological conditions, including those influenced by physical activity, drugs and stress, is crucial to accurately assess cardiac health. However, current AI-based methods often fail to account for how these factors interact and alter ECG patterns, ultimately limiting their applicability in real-world settings. This study introduces IKrNet, a novel neural network model, which identifies drug-specific patterns in ECGs amidst certain physiological conditions. IKrNet's architecture incorporates spatial and temporal dynamics by using a convolutional backbone with varying receptive field size to capture spatial features. A bi-directional Long Short-Term Memory module is also employed to model temporal dependencies. By treating heart rate variability as a surrogate for physiological fluctuations, we evaluated IKrNet's performance across diverse scenarios, including conditions with physical stress, drug intake alone, and a baseline without drug presence. Our assessment follows a clinical protocol in which 990 healthy volunteers were administered 80mg of Sotalol, a drug which is known to be a precursor to Torsades-de-Pointes, a life-threatening arrhythmia. We show that IKrNet outperforms state-of-the-art models' accuracy and stability in varying physiological conditions, underscoring its clinical viability.

Haoran Sun, Dominique Fourer, Hichem Maaref

Dynamic Range Compression (DRC) is a widely used audio effect that adjusts signal dynamics for applications in music production, broadcasting, and speech processing. Inverting DRC is of broad importance for restoring the original dynamics, enabling remixing, and enhancing the overall audio quality. Existing DRC inversion methods either overlook key parameters or rely on precise parameter values, which can be challenging to estimate accurately. To address this limitation, we introduce a hybrid approach that combines model-based DRC inversion with neural networks to achieve robust DRC parameter estimation and audio restoration simultaneously. Our method uses tailored neural network architectures (classification and regression), which are then integrated into a model-based inversion framework to reconstruct the original signal. Experimental evaluations on various music and speech datasets confirm the effectiveness and robustness of our approach, outperforming several state-of-the-art techniques.

Dominique Fourer, Geoffroy Peeters

We propose a novel unsupervised singing voice detection method which use single-channel Blind Audio Source Separation (BASS) algorithm as a preliminary step. To reach this goal, we investigate three promising BASS approaches which operate through a morphological filtering of the analyzed mixture spectrogram. The contributions of this paper are manyfold. First, the investigated BASS methods are reworded with the same formalism and we investigate their respective hyperparameters by numerical simulations. Second, we propose an extension of the KAM method for which we propose a novel training algorithm used to compute a source-specific kernel from a given isolated source signal. Second, the BASS methods are compared together in terms of source separation accuracy and in terms of singing voice detection accuracy when they are used in our new singing voice detection framework. Finally, we do an exhaustive singing voice detection evaluation for which we compare both supervised and unsupervised singing voice detection methods. Our comparison explores different combination of the proposed BASS methods with new features such as the new proposed KAM features and the scattering transform through a machine learning framework and also considers convolutional neural networks methods.