Romain Serizel

Romain Serizel

Auto-generated profile, based on publicly available information

Romain Serizel

Multispeech team, Universit de Lorraine, CNRS, Inria, Loria, Nancy, France

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
6 June 2021
Verified
Conference Paper
Open access
GFGiacomo Ferroni
Giacomo Ferroni
NTNicolas Turpault
Nicolas Turpault
JAJuan Azcarreta
Juan Azcarreta
FTFrancesco Tuveri
Francesco Tuveri
RSRomain Serizel
Romain Serizel
SKSacha Krstulovic
Sacha Krstulovic
The ranking of sound event detection (SED) systems may be biased by assumptions inherent to evaluation criteria and to the choice of an operating point. This paper compares conventional event-based and segment-based criteria against the Polyphonic Sound Detection Score (PSDS)'s intersection-based criterion, over a selection of systems from DCASE 2020 Challenge Task 4. It shows that, by relying on collars, the conventional event-based criterion introduces different strictness levels depending on the length of the sound events, and that the segment-based criterion may lack precision and be application dependent. Alternatively, PSDS's intersection-based criterion overcomes the dependency of the evaluation on sound event duration and provides robustness to labelling subjectivity, by allowing valid detections of interrupted events. Furthermore, PSDS enhances the comparison of SED systems by measuring sound event modelling performance independently from the systems' operating points.

23 May 2022
Verified
Conference Paper
Open access
FRFrancesca Ronchini
Francesca Ronchini
RSRomain Serizel
Romain Serizel
This paper proposes a benchmark of submissions to Detection and Classification Acoustic Scene and Events 2021 Challenge (DCASE) Task 4 representing a sampling of the state-of-the-art in Sound Event Detection task. The submissions are evaluated according to the two polyphonic sound detection score scenarios proposed for the DCASE 2021 Challenge Task 4, which allow to make an analysis on whether submissions are designed to perform fine-grained temporal segmentation, coarse-grained temporal segmentation, or have been designed to be polyvalent on the scenarios proposed.We study the solutions proposed by participants to analyze their robustness to varying level target to non-target signal-to-noise ratio and to temporal localization of target sound events. A last experiment is proposed in order to study the impact of non-target events on systems outputs. Results show that systems adapted to provide coarse segmentation outputs are more robust to different target to non-target signal-to-noise ratio and, with the help of specific data augmentation methods, they are more robust to time localization of the original event. Results of the last experiment display that systems tend to spuriously predict short events when non-target events are present. This is particularly true for systems that are tailored to have a fine segmentation.

10 November 2016
Verified
Conference Paper
Open access
RSRomain Serizel
Romain Serizel
SESlim Essid
Slim Essid
GRGael Richard
Gael Richard
Nonnegative matrix factorisation (NMF) with β-divergence is a popular method to decompose real world data. In this paper we propose mini-batch stochastic algorithms to perform NMF efficiently on large data matrices. Besides the stochastic aspect, the mini-batch approach allows exploiting intensive computing devices such as general purpose graphical processing units to decrease the processing time and in some cases outperform coordinate descent approach.

27 June 2025 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
MSMostafa Sadeghi
Mostafa Sadeghi
JAJean-Eudes Ayilo
Jean-Eudes Ayilo
RSRomain Serizel
Romain Serizel
Xavier Alameda-PinedaXavier Alameda-Pineda
Xavier Alameda-Pineda
We explore unsupervised speech enhancement using diffusion models as expressive generative priors for clean speech. Existing approaches guide the reverse diffusion process using noisy speech through an approximate, noise-perturbed likelihood score, combined with the unconditional score via a trade-off hyperparameter. In this work, we propose two alternative algorithms that directly model the conditional reverse transition distribution of diffusion states. The first method integrates the diffusion prior with the observation model in a principled way, removing the need for hyperparameter tuning. The second defines a diffusion process over the noisy speech itself, yielding a fully tractable and exact likelihood score. Experiments on the WSJ0-QUT and VoiceBank-DEMAND datasets demonstrate improved enhancement metrics and greater robustness to domain shifts compared to both supervised and unsupervised baselines.

12 June 2026 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
JAJean-Eudes Ayilo
Jean-Eudes Ayilo
MSMostafa Sadeghi
Mostafa Sadeghi
RSRomain Serizel
Romain Serizel
Xavier Alameda-PinedaXavier Alameda-Pineda
Xavier Alameda-Pineda
This paper addresses unsupervised diffusion-based single-channel speech enhancement (SE). Prior work in this direction combines a score-based diffusion model trained on clean speech with a Gaussian noise model whose covariance is structured by non-negative matrix factorization (NMF). This combination is used within an iterative expectation-maximization (EM) scheme, in which a diffusion-based posterior-sampling E-step estimates the clean speech. We first revisit this framework and propose to explicitly model both speech and acoustic noise as latent variables, jointly sampling them in the E-step instead of sampling speech alone as in previous approaches. We then introduce a new semi-supervised SE framework that replaces the NMF noise prior with a diffusion-based noise model, learned jointly with the speech prior in a single conditional score model. Within this framework, we derive two variants: one that implicitly accounts for noise and one that explicitly treats noise as a latent variable. Experiments on WSJ0–QUT and VoiceBank–DEMAND show that explicit noise modeling systematically improves SE performance for both NMF-based and diffusion-based noise priors. Under matched conditions, the diffusion-based noise model attains the best overall quality and intelligibility among unsupervised methods, while under mismatched conditions the proposed NMF-based explicit-noise framework is more robust and suffers less degradation than several supervised baselines. Code, demo, and supplementary materials are publicly available.

6 November 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
CLCharly Lamothe
Charly Lamothe
AVAntonin Verdier
Antonin Verdier
CCCorentin Caris
Corentin Caris
RGRyan Greer
Ryan Greer
RORomain Oliveira
Romain Oliveira
BBBrice Bathellier
Brice Bathellier
Cochlear and auditory brainstem implants are the primary treatments for profound deafness 1 . However, the inherently low resolution of electrical stimulation used by these devices limits information transfer to a small number of independent stimulation channels 2 and results in perceptual difficulties. An alternative approach is to target the auditory cortex, a brain region large enough to accommodate hundreds of stimulation channels and whose stimulation evokes sound percepts 3,4 . Although modern brain interfaces offer large channel counts and spatial resolution, developing encoding algorithms capable of accurately transmitting interpretable sound information remains challenging. Here we introduce Braincodec, a deep network that optimizes both sound information transmission and the alignment of stimulation patterns with the spatial, temporal, and high-level properties of the auditory cortex neural code. Braincodec operates online and requires only a few hundred channels to transmit sufficient information for the reconstruction of natural sounds with high fidelity, a performance inaccessible to cochlear implant encoders. Moreover, mice equipped with a Braincodec-driven auditory cortical prosthesis matched the accuracy of non-implanted mice in discriminating real sounds. Braincodec therefore enables the development of high-throughput cortical neuroprosthetics with the potential to overcome the limitations of current auditory implants and provides a generic framework applicable to other sensory modalities.