Romain Serizel

119
Documents

Présentation

I was born in Lille, France. I received the M.Eng. degree in Automatic System Engineering from ENSEM (Nancy, France) in 2005 and the M.Sc. degree in Signal Processing from Université Rennes 1 (Rennes, France) in 2006. I received the Ph.D. degree in Engineering Sciences from the Katholieke Universiteit Leuven (KUL), Belgium in June 2011. From June 2011 to December 2012 I was a research assistant with Prof. Marc Moonen research group at the Electrical Engineering Department (ESAT-SCD) of the KUL. From January 2013 to September 2014 i was a postdoctoral researcher with the Human Language Technology (HLT) group at the Fondazione Bruno Kessler (FBK) in Trento (Italy). From October 2014 to August 2016 I was a postdoctoral researcher with the department of signal and image processing (TSI) at telecom ParisTech in Paris (France) where I am working on speaker diarization, speaker recognition and respresentation learning for audio in the framework of the LASIE project. I am now an assistant professor at Université de Lorraine doing my research in Laboratoire lorrain de recherche en informatique et ses applications (Loria) with the Multispeech research group and teaching at IUT Charlemagne.

Publications

Publications

Deposit thumbnail

Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement

Mostafa Sadeghi , Jean-Eudes Ayilo , Romain Serizel , Xavier Alameda-Pineda

IEEE Signal Processing Letters, 2025, 32, pp.2694-2698. ⟨10.1109/LSP.2025.3583967⟩

Article dans une revue hal-05135495v1

Reducing noise with augmented reality in indoor soundscapes

Nicolas Misdariis , Mathieu Lagrange , Romain Serizel

Journal of the Acoustical Society of America, 2024, 155 (3_Supplement), pp.A179-A179. ⟨10.1121/10.0027235⟩

Article dans une revue hal-05302537v1
Deposit thumbnail

Evaluating and predicting the audibility of acoustic alarms in the workplace using experimental methods and deep learning

François Effa , Jean-Pierre Arz , Romain Serizel , Nicolas Grimault

Applied Acoustics, 2024, 219, pp.109955. ⟨10.1016/j.apacoust.2024.109955⟩

Article dans une revue hal-04645900v1
Deposit thumbnail

A Phoneme-Scale Assessment of Multichannel Speech Enhancement Algorithms

Nasser-Eddine Monir , Paul Magron , Romain Serizel

Trends in Hearing, 2024, 28, ⟨10.1177/23312165241292205⟩

Article dans une revue hal-04854449v1
Deposit thumbnail

DNN-based mask estimation for distributed speech enhancement in spatially unconstrained microphone arrays

Nicolas Furnon , Romain Serizel , Slim Essid , Irina Illina

IEEE/ACM Transactions on Audio, Speech and Language Processing, 2021, 29, pp.2310 - 2323. ⟨10.1109/TASLP.2021.3092838⟩

Article dans une revue hal-02985867v3
Deposit thumbnail

Joint NN-Supported Multichannel Reduction of Acoustic Echo, Reverberation and Noise

Guillaume Carbajal , Romain Serizel , Emmanuel Vincent , Eric Humbert

IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, ⟨10.1109/TASLP.2020.3008974⟩

Article dans une revue hal-02372579v4
Deposit thumbnail

Audio-Based Search and Rescue with a Drone: Highlights from the IEEE Signal Processing Cup 2019 Student Competition

Antoine Deleforge , Diego Di Carlo , Martin Strauss , Romain Serizel , Lucio Marcenaro

IEEE Signal Processing Magazine, 2019, 36 (5), pp.138-144. ⟨10.1109/MSP.2019.2924687⟩

Article dans une revue hal-02161897v1
Deposit thumbnail

CRNN-based multiple DoA estimation using acoustic intensity features for Ambisonics recordings

Lauréline Perotin , Romain Serizel , Emmanuel Vincent , Alexandre Guérin

IEEE Journal of Selected Topics in Signal Processing, 2019, Special Issue on Acoustic Source Localization and Tracking in Dynamic Real-life Scenes, 13 (1), pp.22-33. ⟨10.1109/jstsp.2019.2900164⟩

Article dans une revue hal-01839883v2
Deposit thumbnail

Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments

Ziteng Wang , Emmanuel Vincent , Romain Serizel , Yonghong Yan

Computer Speech and Language, 2018, 49, pp.37-51. ⟨10.1016/j.csl.2017.11.003⟩

Article dans une revue hal-01634449v1
Deposit thumbnail

Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification

Victor Bisot , Romain Serizel , Slim Essid , Gael Richard

IEEE/ACM Transactions on Audio, Speech and Language Processing, 2017, 25 (6), pp.1216 - 1229. ⟨10.1109/TASLP.2017.2690570⟩

Article dans une revue hal-01362864v2
Deposit thumbnail

Deep-neural network approaches for speech recognition with heterogeneous groups of speakers including children

Romain Serizel , Diego Giuliani

Natural Language Engineering, 2016, 1, pp.0 - 0

Article dans une revue hal-01390905v1
Deposit thumbnail

Low-rank Approximation Based Multichannel Wiener Filter Algorithms for Noise Reduction with Application in Cochlear Implants

Romain Serizel , Marc Moonen , Bas van Dijk , Jan Wouters

IEEE/ACM Transactions on Audio, Speech and Language Processing, 2014, 22, pp.785 - 799. ⟨10.1109/TASLP.2014.2304240⟩

Article dans une revue hal-01390918v1
Deposit thumbnail

Binaural Integrated Active Noise Control and Noise Reduction in Hearing Aids

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

IEEE Transactions on Audio, Speech and Language Processing, 2013, 21 (5), pp.1113-1118

Article dans une revue hal-01393937v1
Deposit thumbnail

A Speech Distortion Weighting Based Approach to Integrated Active Noise Control and Noise Reduction in Hearing Aids

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

Signal Processing, 2013, 93 (9), pp.2440-2452

Article dans une revue hal-01393931v1
Deposit thumbnail

A Zone of Quiet Based Approach to Integrated Active Noise Control and Noise Reduction for Speech Enhancement in Hearing Aids

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

IEEE Transactions on Audio, Speech and Language Processing, 2012, 20 (6), pp.1685 - 1697

Article dans une revue hal-01393939v1
Deposit thumbnail

Output SNR analysis of integrated active noise control and noise reduction in hearing aids under a single speech source scenario

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

Signal Processing, 2011, 91 (8), pp.1719-1729

Article dans une revue hal-01393940v1

Accuracy Constraint Determination in Fixed-Point System Design

Daniel Menard , Romain Serizel , Romuald Rocher , Olivier Sentieys

EURASIP Journal on Embedded Systems, 2008, 2008 (1), ⟨10.1155/2008/242584⟩

Article dans une revue inria-00459254v1
Deposit thumbnail

Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models

Riccardo Passoni , Francesca Ronchini , Luca Comanducci , Romain Serizel , Fabio Antonacci

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2025, Granlibakken Tahoe, United States

Communication dans un congrès hal-05468351v1
Deposit thumbnail

Speaker Embeddings to Improve Tracking of Intermittent and Moving Speakers

Taous Iatariene , Can Cui , Alexandre Guérin , Romain Serizel

33rd European Signal Processing Conference (EUSIPCO 2025), Sep 2025, Palerme (Italie), Italy

Communication dans un congrès hal-05001491v2
Deposit thumbnail

Diffusion-based Unsupervised Audio-visual Speech Enhancement

Jean-Eudes Ayilo , Mostafa Sadeghi , Romain Serizel , Xavier Alameda-Pineda

ICASSP 2025 - International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2025, Hyderabad, India. pp.1-5

Communication dans un congrès hal-04718254v2
Deposit thumbnail

A decade of DCASE: Achievements, practices, evaluations and future challenges

Annamaria Mesaros , Romain Serizel , Toni Heittola , Tuomas Virtanen , Mark Plumbley

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2025, Hyderabad, France. pp.1-5, ⟨10.1109/ICASSP49660.2025.10887673⟩

Communication dans un congrès hal-05468341v1
Deposit thumbnail

Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings

Taous Iatariene , Alexandre Guérin , Romain Serizel

2025 IEEE 27th International Workshop on Multimedia Signal Processing (MMSP), Sep 2025, Beijin, China

Communication dans un congrès hal-05212018v1
Deposit thumbnail

Evaluating Multichannel Speech Enhancement Algorithms at the Phoneme Scale Across Genders

Nasser-Eddine Monir , Paul Magron , Romain Serizel

33rd European Signal Processing Conference, Sep 2025, Palerme, Italy. ⟨10.48550/arXiv.2506.18691⟩

Communication dans un congrès hal-05328713v1
Deposit thumbnail

Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement

Nasser-Eddine Monir , Paul Magron , Romain Serizel

IEEE 27th International Workshop on Multimedia Signal Processing, Sep 2025, Beijing, China. ⟨10.48550/arXiv.2506.18714⟩

Communication dans un congrès hal-05328729v1
Deposit thumbnail

Phoneme-Level Speech Intelligibility Reduction

Aine Drelingyte , Romain Serizel , Mathieu Lagrange

EUSIPCO 2025 - 33rd European Signal Processing Conference, Sep 2025, Palerme, Italy

Communication dans un congrès hal-05172656v1
Deposit thumbnail

Tracking of Intermittent and Moving Speakers : Dataset and Metrics

Taous Iatariene , Alexandre Guérin , Romain Serizel

Proceedings of the 11th Convention of the European Acoustics Association Forum Acusticum 2025, Jun 2025, Malaga, Espagne, Spain

Communication dans un congrès hal-05058365v1
Deposit thumbnail

Unsupervised speech enhancement with diffusion-based generative models

Berné Nortier , Mostafa Sadeghi , Romain Serizel

International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Apr 2024, Seoul (Korea), South Korea. ⟨10.48550/arXiv.2309.10450⟩

Communication dans un congrès hal-04210707v2
Deposit thumbnail

Normalizing Energy Consumption for Hardware-Independent Evaluation

Constance Douwes , Romain Serizel

2024 IEEE International Workshop on Machine Learning for Signal Processing, Sep 2024, London, United Kingdom

Communication dans un congrès hal-04697122v1
Deposit thumbnail

A weighted-variance variational autoencoder model for speech enhancement

Ali Golmakani , Mostafa Sadeghi , Xavier Alameda-Pineda , Romain Serizel

ICASSP 2024 - International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), South Korea. pp.1-5, ⟨10.1109/ICASSP48485.2024.10446294⟩

Communication dans un congrès hal-03833827v2
Deposit thumbnail

Mixture of Mixups for Multi-label Classification of Rare Anuran Sounds

Ilyass Moummad , Nicolas Farrugia , Romain Serizel , Jeremy Froidevaux , Vincent Lostanlen

EUSIPCO 2024: 32nd European Signal Processing Conference, Aug 2024, Lyon, France. pp.1282-1286, ⟨10.23919/EUSIPCO63174.2024.10715140⟩

Communication dans un congrès hal-04620733v1
Deposit thumbnail

Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder

Mostafa Sadeghi , Romain Serizel

International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Apr 2024, Seoul (Korea), South Korea. ⟨10.48550/arXiv.2309.10439⟩

Communication dans un congrès hal-04210679v2
Deposit thumbnail

Self-Supervised Learning for Few-Shot Bird Sound Classification

Ilyass Moummad , Nicolas Farrugia , Romain Serizel

ICASSPW 2024: IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSPW62465.2024.10627576⟩

Communication dans un congrès hal-04925735v1
Deposit thumbnail

RoboVox: A Single/Multi-channel Far-field Speaker Recognition Benchmark for a Mobile Robot

Mohammad Mohammadamini , Driss Matrouf , Michael Rouvier , Jean-Francois Bonastre , Romain Serizel et al.

LREC_COLING, ELRA, May 2024, Turino, Italy

Communication dans un congrès hal-04536499v1
Deposit thumbnail

From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems

Constance Douwes , Romain Serizel

Detection and Classification of Acoustic Scenes and Events 2024, Oct 2024, Tokyo, Japan

Communication dans un congrès hal-04697137v1
Deposit thumbnail

Regularized Contrastive Pre-Training for Few-Shot Bioacoustic Sound Detection

Ilyass Moummad , Nicolas Farrugia , Romain Serizel

ICASSP 2024: IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSP48485.2024.10446409⟩

Communication dans un congrès hal-04925734v1
Deposit thumbnail

Performance and Energy Balance: A Comprehensive Study of State-of-the-Art Sound Event Detection Systems

Francesca Ronchini , Romain Serizel

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.1096-1100, ⟨10.1109/ICASSP48485.2024.10445834⟩

Communication dans un congrès hal-04892368v1
Deposit thumbnail

Diffusion-based speech enhancement with a weighted generative-supervised learning loss

Jean-Eudes Ayilo , Mostafa Sadeghi , Romain Serizel

International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Apr 2024, Seoul (Korea), South Korea. ⟨10.48550/arXiv.2309.10457⟩

Communication dans un congrès hal-04210729v2
Deposit thumbnail

Multi-channel extension of pre-trained models for speaker verification

Ladislav Mošner , Romain Serizel , Lukáš Burget , Oldřich Plchot , Emmanuel Vincent et al.

Interspeech, Sep 2024, Kos, Greece

Communication dans un congrès hal-04667593v1

Monitoring environmental impact of DCASE systems: Why and how ?

Constance Douwes , Francesca Ronchini , Romain Serizel

Detection and Classification of Acoustic Scene and Events (DCASE) Workshop, Sep 2023, Tampere (Finlande), Finland

Communication dans un congrès hal-04286654v1
Deposit thumbnail

Performance above all ? energy consumption vs. performance for machine listening, a study on dcase task 4 baseline

Romain Serizel , Samuele Cornell , Nicolas Turpault

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, France. pp.1-5, ⟨10.1109/ICASSP49357.2023.10095938⟩

Communication dans un congrès hal-03850797v1
Deposit thumbnail

Post-Processing Independent Evaluation of Sound Event Detection Systems

Janek Ebbers , Reinhold Haeb-Umbach , Romain Serizel

DCASE 2023 - 8th Workshop on Detection and Classification of Acoustic Scenes and Events, Sep 2023, Tampere, Finland. ⟨10.48550/arXiv.2306.15440⟩

Communication dans un congrès hal-04385022v1
Deposit thumbnail

Self-supervised learning with diffusion-based multichannel speech enhancement for speaker verification under noisy conditions

Sandipana Dowerah , Ajinkya Kulkarni , Romain Serizel , Denis Jouvet

INTERSPEECH 2023, Aug 2023, Dublin (Ireland), Ireland. pp.3849-3853, ⟨10.21437/Interspeech.2023-1890⟩

Communication dans un congrès hal-04151411v1
Deposit thumbnail

Pretraining Representations for Bioacoustic Few-Shot Detection using Supervised Contrastive Learning

Ilyass Moummad , Romain Serizel , Nicolas Farrugia

Detection and Classification of Acoustic Scenes and Events 2023, Sep 2023, TAMPERE, Finland

Communication dans un congrès hal-04383609v1
Deposit thumbnail

Fast and efficient speech enhancement with variational autoencoders

Mostafa Sadeghi , Romain Serizel

International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Jun 2023, Rhodes island, Greece

Communication dans un congrès hal-03833836v2
Deposit thumbnail

Joint optimization of diffusion probabilistic-based multichannel speech enhancement with far-field speaker verification

Sandipana Dowerah , Romain Serizel , Denis Jouvet , M Mohammadamini , Driss Matrouf

IEEE SLT 2022, Jan 2023, Doha, Qatar

Communication dans un congrès hal-03671583v2
Deposit thumbnail

Lightweight Annotation and Class Weight Training for Automatic Estimation of Alarm Audibility in Noise

François Effa , Romain Serizel , Jean-Pierre Arz , Nicolas Grimault

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10094730⟩

Communication dans un congrès hal-04385004v1
Deposit thumbnail

SPICE+: Evaluation of automatic audio captioning systems with pre-trained language models

Félix Gontier , Romain Serizel , Christophe Cerisara

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), Jun 2023, Rhodes Island, Greece

Communication dans un congrès hal-03933981v1
Deposit thumbnail

BinauRec: A dataset to test the influence of the use of room impulse responses on binaural speech enhancement

Louis Delebecque , Romain Serizel

EUSIPCO23, EURASIP, Sep 2023, Helsiinki, Finland. ⟨10.23919/EUSIPCO58844.2023.10289772⟩

Communication dans un congrès hal-04193377v1
Deposit thumbnail

From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion

Robin San Roman , Yossi Adi , Antoine Deleforge , Romain Serizel , Gabriel Synnaeve et al.

NeurIPS 2023 - Conference on Neural Information Processing Systems, Dec 2023, New Orleans, United States. ⟨10.48550/arXiv.2308.02560⟩

Communication dans un congrès hal-04385071v1
Deposit thumbnail

Audio-visual speech enhancement with a deep kalman filter generative model

Ali Golmakani , Mostafa Sadeghi , Romain Serizel

International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Jun 2023, Rhodes island, Greece

Communication dans un congrès hal-03833814v2
Deposit thumbnail

CONVOLUTIONAL NEURAL NETWORK FOR AUDIBILITY ASSESSMENT OF ACOUSTIC ALARMS

François Effa , Romain Serizel , Jean-Pierre Arz , Nicolas Grimault

International Conference on Acoustics, Speech and Signal Processing Search form Search ICASSP IEEE 2023, Jun 2023, Rhodes, Greece

Communication dans un congrès hal-04010329v1
Deposit thumbnail

Learning noise robust ResNet-based speaker embedding for speaker recognition

Mohammad Mohammadamini , Driss Matrouf , Jean-François Bonastre , Sandipana Dowerah , Romain Serizel et al.

Odyssey 2022 : The Speaker and Language Recognition Workshop, Jun 2022, Beijing, China

Communication dans un congrès hal-03650549v1
Deposit thumbnail

Threshold independent evaluation of sound event detection scores

Janek Ebbers , Reinhold Haeb-Umbach , Romain Serizel

ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. ⟨10.1109/ICASSP43922.2022.9747556⟩

Communication dans un congrès hal-03562763v1
Deposit thumbnail

Barlow Twins self-supervised learning for robust speaker recognition

Mohammad Mohammadamini , Driss Matrouf , Jean-François A Bonastre , Sandipana Dowerah , Romain Serizel et al.

Interspeech 2022 - Human and Humanizing Speech Technology, Sep 2022, Incheon, South Korea. ⟨10.21437/Interspeech.2022-11301⟩

Communication dans un congrès hal-03710445v2
Deposit thumbnail

Integrating isolated examples with weakly-supervised sound event detection: a direct approach

Mohammad Abdollahi , Romain Serizel , Alain Rakotomamonjy , Gilles Gasso

7th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), Nov 2022, Nancy, France

Communication dans un congrès hal-03894965v1

Evaluation de l’audibilité ressentie des alarmes sonores dans le bruit

Jean-Pierre Arz , François Effa , Nicolas Grimault , Romain Serizel

16ème Congrès Français d'Acoustique, CFA2022, Société Française d'Acoustique; Laboratoire de Mécanique et d'Acoustique, Apr 2022, Marseille, France

Communication dans un congrès hal-03848387v1
Deposit thumbnail

A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes

Francesca Ronchini , Romain Serizel

ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore/Virtual, Singapore. ⟨10.1109/ICASSP43922.2022.9747577⟩

Communication dans un congrès hal-03554305v2
Deposit thumbnail

How to Leverage DNN-based speech enhancement for multi-channel speaker verification?

Sandipana Dowerah , Romain Serizel , Denis Jouvet , Mohammad Mohammadamini , Driss Matrouf

4th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2022), Oct 2022, Corfu, Greece

Communication dans un congrès hal-03619903v2

Modélisation de la détection d’alarmes sonores dans le bruit

François Effa , Jean-Pierre Arz , Nicolas Grimault , Ossen El Sawaf , Romain Serizel

16ème Congrès Français d'Acoustique, CFA2022, Société Française d'Acoustique; Laboratoire de Mécanique et d'Acoustique, Apr 2022, Marseille, France

Communication dans un congrès hal-03848388v1
Deposit thumbnail

A Comprehensive Exploration of Noise Robustness and Noise Compensation in ResNet and TDNN-based Speaker Recognition Systems

Mohammad Mohammadamini , Driss Matrouf , Jean-François Bonastre , Sandipana Dowerah , Romain Serizel et al.

EUSIPCO 2022 - 30th European Signal Processing Conference, Aug 2022, Belgrade, Serbia

Communication dans un congrès hal-03669919v1
Deposit thumbnail

Foreground-Background Ambient Sound Scene Separation

Michel Olvera , Emmanuel Vincent , Romain Serizel , Gilles Gasso

EUSIPCO 2020 - 28th European Signal Processing Conference, Jan 2021, Amsterdam / Virtual, Netherlands. ⟨10.23919/Eusipco47968.2020.9287436⟩

Communication dans un congrès hal-02567542v2
Deposit thumbnail

UIAI System for Short-Duration Speaker Verification Challenge 2020

Md Sahidullah , Achintya Kumar Sarkar , Ville Vestman , Xuechen Liu , Romain Serizel et al.

SLT 2021 - IEEE Spoken Language Technology Workshop, IEEE, Jan 2021, Shenzhen / Virtual, China. ⟨10.1109/SLT48900.2021.9383596⟩

Communication dans un congrès hal-02907037v2
Deposit thumbnail

What’s All the FUSS About Free Universal Sound Separation Data?

Scott Wisdom , Hakan Erdogan , Daniel P W Ellis , Romain Serizel , Nicolas Turpault et al.

ICASSP 2021 - 46th International Conference on Acoustics, Speech, and Signal Processing, Jun 2021, Toronto/Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414774⟩

Communication dans un congrès hal-02984693v1
Deposit thumbnail

Automated audio captioning by fine-tuning bart with audioset tags

Félix Gontier , Romain Serizel , Christophe Cerisara

DCASE 2021 - 6th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2021, Virtual, Spain

Communication dans un congrès hal-03522488v1
Deposit thumbnail

Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

Nicolas Furnon , Romain Serizel , Slim Essid , Irina Illina

EUSIPCO 2021 - 29th European Signal Processing Conference, IEEE, Aug 2021, Dublin / Virtual, Ireland. ⟨10.23919/EUSIPCO54536.2021.9616358⟩

Communication dans un congrès hal-03259801v1
Deposit thumbnail

Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes

Nicolas Turpault , Romain Serizel , Scott Wisdom , Hakan Erdogan , John R Hershey et al.

ICASSP 2021 - 46th International Conference on Acoustics, Speech, and Signal Processing, Jun 2021, Toronto/Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414789⟩

Communication dans un congrès hal-02984675v1
Deposit thumbnail

Distributed speech separation in spatially unconstrained microphone arrays

Nicolas Furnon , Romain Serizel , Irina Illina , Slim Essid

ICASSP 2021 - 46th International Conference on Acoustics, Speech, and Signal Processing, Jun 2021, Toronto / Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414758⟩

Communication dans un congrès hal-02985794v3
Deposit thumbnail

Improving Sound Event Detection Metrics: Insights from DCASE 2020

Giacomo Ferroni , Nicolas Turpault , Juan Azcarreta , Francesco Tuveri , Romain Serizel et al.

ICASSP 2021 - 46th International Conference on Acoustics, Speech, and Signal Processing, Jun 2021, Toronto/Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414711⟩

Communication dans un congrès hal-02978422v1
Deposit thumbnail

The impact of non-target events in synthetic soundscapes for sound event detection

Francesca Ronchini , Romain Serizel , Nicolas Turpault , Samuele Cornell

DCASE 2021 - Detection and Classification of Acoustic Scenes and Events, Nov 2021, Barcelona/Virtual, Spain

Communication dans un congrès hal-03355184v1
Deposit thumbnail

Compensate multiple distortions for speaker recognition systems

Mohammad Mohammadamini , Driss Matrouf , Jean-Francois Bonastre , Romain Serizel , Sandipana Dowerah et al.

EUSIPCO 2021 - 29th European Signal Processing Conference, Aug 2021, Dublin / Virtual, Ireland. ⟨10.23919/EUSIPCO54536.2021.9615983⟩

Communication dans un congrès hal-03224675v1
Deposit thumbnail

A brief introduction to multichannel noise reduction with deep neural networks

Romain Serizel

SpiN 2020 - 12th Speech in Noise Workshop, Jan 2020, Toulouse, France

Communication dans un congrès hal-02506387v1
Deposit thumbnail

Improving Sound Event Detection In Domestic Environments Using Sound Separation

Nicolas Turpault , Scott Wisdom , Hakan Erdogan , John R Hershey , Romain Serizel et al.

DCASE Workshop 2020 - Detection and Classification of Acoustic Scenes and Events, Nov 2020, Tokyo / Virtual, Japan

Communication dans un congrès hal-02891700v4
Deposit thumbnail

DNN-Based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays

Nicolas Furnon , Romain Serizel , Irina Illina , Slim Essid

ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain

Communication dans un congrès hal-02389159v3
Deposit thumbnail

Training Sound Event Detection On A Heterogeneous Dataset

Nicolas Turpault , Romain Serizel

DCASE Workshop, Nov 2020, Tokyo, Japan

Communication dans un congrès hal-02891665v2
Deposit thumbnail

Sound event detection in synthetic domestic environments

Romain Serizel , Nicolas Turpault , Ankit Shah , Justin Salamon

ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain

Communication dans un congrès hal-02355573v2
Deposit thumbnail

Limitations of weak labels for embedding and tagging

Nicolas Turpault , Romain Serizel , Emmanuel Vincent

ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain

Communication dans un congrès hal-02467401v4
Deposit thumbnail

Semi-supervised triplet loss based learning of ambient audio embeddings

Nicolas Turpault , Romain Serizel , Emmanuel Vincent

ICASSP 2019, May 2019, Brighton, United Kingdom

Communication dans un congrès hal-02025824v1
Deposit thumbnail

Sound event detection in domestic environments with weakly labeled data and soundscape synthesis

Nicolas Turpault , Romain Serizel , Ankit Parag Shah , Justin Salamon

Workshop on Detection and Classification of Acoustic Scenes and Events, Oct 2019, New York City, United States

Communication dans un congrès hal-02160855v2
Deposit thumbnail

Regression versus classification for neural network based audio source localization

Lauréline Perotin , Alexandre Défossez , Emmanuel Vincent , Romain Serizel , Alexandre Guérin

WASPAA 2019 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, IEEE, Oct 2019, New Paltz, United States

Communication dans un congrès hal-02125985v2
Deposit thumbnail

Sound Event Detection from Partially Annotated Data: Trends and Challenges

Romain Serizel , Nicolas Turpault

IcETRAN conference, Jun 2019, Srebrno Jezero, Serbia

Communication dans un congrès hal-02114652v2
Deposit thumbnail

Multiple-input neural network-based residual echo suppression

Guillaume Carbajal , Romain Serizel , Emmanuel Vincent , Eric Humbert

ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Canada. pp.1-5

Communication dans un congrès hal-01723630v2
Deposit thumbnail

Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments

Romain Serizel , Nicolas Turpault , Hamid Eghbal-Zadeh , Ankit Parag Shah

Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2018, Woking, United Kingdom

Communication dans un congrès hal-01850270v1
Deposit thumbnail

Multichannel speech separation with recurrent neural networks from high-order ambisonics recordings

Lauréline Perotin , Romain Serizel , Emmanuel Vincent , Alexandre Guérin

43rd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018), Apr 2018, Calgary, Canada

Communication dans un congrès hal-01699759v2
Deposit thumbnail

Multichannel Audio Modeling with Elliptically Stable Tensor Decomposition

Mathieu Fontaine , Fabian-Robert Stöter , Antoine Liutkus , Umut Şimşekli , Romain Serizel et al.

LVA/ICA 2018 - 14th International Conference on Latent Variable Analysis and Signal Separation, Jul 2018, Surrey, United Kingdom. pp.13-23, ⟨10.1007/978-3-319-93764-9_2⟩

Communication dans un congrès lirmm-01766795v1
Deposit thumbnail

CRNN-based joint azimuth and elevation localization with the Ambisonics intensity vector

Lauréline Perotin , Romain Serizel , Emmanuel Vincent , Alexandre Guérin

IWAENC 2018 - 16th International Workshop on Acoustic Signal Enhancement, Sep 2018, Tokyo, Japan

Communication dans un congrès hal-01840453v1
Deposit thumbnail

Leveraging deep neural networks with nonnegative representations for improved environmental sound classification

Victor Bisot , Romain Serizel , Slim Essid , Gael Richard

IEEE International Workshop on Machine Learning for Signal Processing MLSP, Sep 2017, Tokyo, Japan

Communication dans un congrès hal-01576857v1
Deposit thumbnail

Supervised Group Nonnegative Matrix Factorisation With Similarity Constraints And Applications To Speaker Identification

Romain Serizel , Victor Bisot , Slim Essid , Gael Richard

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Mar 2017, New Orleans, United States

Communication dans un congrès hal-01484744v1
Deposit thumbnail

Nonnegative Feature Learning Methods for Acoustic Scene Classification

Victor Bisot , Romain Serizel , Slim Essid , Gael Richard

DCASE 2017 - Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2017, Munich, Germany

Communication dans un congrès hal-01636627v1

Acoustic scene classification with matrix factorization for unsupervised feature learning

Victor Bisot , Romain Serizel , Slim Essid , Gael Richard

ICASSP, Mar 2016, Shangai, China

Communication dans un congrès hal-02287267v1
Deposit thumbnail

Machine listening techniques as a complement to video image analysis in forensics

Romain Serizel , Victor Bisot , Slim Essid , Gael Richard

IEEE International Conference on Image Processing, Sep 2016, Phoenix, AZ, United States. pp.948-952, ⟨10.1109/ICIP.2016.7532497⟩

Communication dans un congrès hal-01393959v1
Deposit thumbnail

SUPERVISED NONNEGATIVE MATRIX FACTORIZATION FOR ACOUSTIC SCENE CLASSIFICATION

Victor Bisot , Romain Serizel , Slim Essid , Gael Richard

IEEE international evaluation campaign on detection and classification of acousitc scenes and events (DCASE 2016), Sep 2016, Budapest, Hungary

Communication dans un congrès hal-02943480v1

Group nonnegative matrix factorisation with speaker and session variability compensation for speaker identification

Romain Serizel , Slim Essid , Gael Richard

ICASSP, Mar 2016, Shangai, China. pp.5470 - 5474

Communication dans un congrès hal-02288453v1
Deposit thumbnail

Group Non-Negative Matrix Factorisation With Speaker And Session Similarity Constraints For Speaker Identification

Romain Serizel , Slim Essid , Gael Richard

IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2016, Shangai, China

Communication dans un congrès hal-01393968v1
Deposit thumbnail

Mini-batch stochastic approaches for accelerated multiplicative updates in nonnegative matrix factorisation with beta-divergence

Romain Serizel , Slim Essid , Gael Richard

IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2016), Sep 2016, Salerne, Italy

Communication dans un congrès hal-01393964v1

A brief introduction to deep neural networks and their application to automatic speech recognition

Romain Serizel

Séminaire de l'équipe Perception, Feb 2015, Grenoble, France

Communication dans un congrès hal-02287014v1
Deposit thumbnail

Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition

Romain Serizel , Diego Giuliani

2014 IEEE Spoken Language Technology Workshop (SLT 2014), Dec 2014, South Lake Tahoe, CA, United States. pp.135-140, ⟨10.1109/SLT.2014.7078563⟩

Communication dans un congrès hal-01393972v1
Deposit thumbnail

Deep neural network adaptation for children's and adults' speech recognition

Romain Serizel , Diego Giuliani

Italian Computational Linguistics Conference (CLiC-it), Dec 2014, Pise, Italy

Communication dans un congrès hal-01393975v1
Deposit thumbnail

Rank-1 Approximation Based Multichannel Wiener Filtering Algorithms For Noise Reduction In Cochlear Implants

Romain Serizel , Marc Moonen , Bas Van Dijk , Jan Wouters

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013, Vancouver, Canada

Communication dans un congrès hal-01393980v1
Deposit thumbnail

Output SNR analysis of integrated active noise control and noise reduction in hearing aids under a single speech source scenario

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

European Signal Processing Conference (EUSIPCO), Aug 2010, Aalborg, Denmark

Communication dans un congrès hal-01393977v1
Deposit thumbnail

A Zone of Quiet Based Approach to Integrated Active Noise Control and Noise Reduction in Hearing Aids

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2009, New Paltz, United States

Communication dans un congrès hal-01393983v1
Deposit thumbnail

A Weighted Approach for Integrated Active Noise Control and Noise Reduction in Hearing Aids

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

European Signal Processing Conference (EUSIPCO), Aug 2009, Glasgow, United Kingdom

Communication dans un congrès hal-01393985v1
Deposit thumbnail

Combined Active Noise Control and noise reduction in Hearing Aids

Romain Serizel , Marc Moonen , Jan Wouters , Søren Holdt Jensen

International Workshop on Acoustic Echo and Noise Control (IWAENC), Sep 2008, Seattle, United States

Communication dans un congrès hal-01393988v1

Noise model for Accuracy Constraint Determination in Fixed-Point Systems

Daniel Menard , Romain Serizel , Romuald Rocher , Olivier Sentieys

Workshop on Design and Architectures for Signal and Image Processing DASIP 2007, Nov 2007, Grenoble, France

Communication dans un congrès inria-00459290v1
Deposit thumbnail

Multiview approaches to event detection and scene analysis

Slim Essid , Sanjeel Parekh , Ngoc Q. K. Duong , Romain Serizel , Alexey Ozerov et al.

Tuomas Virtanen; Mark D. Plumbley; Dan Ellis. Computational Analysis of Sound Scenes and Events, Springer, pp.243-276, 2017, 978-3319634494. ⟨10.1007/978-3-319-63450-0_9⟩

Chapitre d'ouvrage hal-01620341v1
Deposit thumbnail

Acoustic Features for Environmental Sound Analysis

Romain Serizel , Victor Bisot , Slim Essid , Gael Richard

Tuomas Virtanen; Mark D. Plumbley; Dan Ellis. Computational Analysis of Sound Scenes and Events, Springer International Publishing AG, pp.71-101, 2017, 978-3-319-63449-4. ⟨10.1007/978-3-319-63450-0_4⟩

Chapitre d'ouvrage hal-01575619v1
Deposit thumbnail

Metric analysis for spatial semantic segmentation of sound scenes

Mayank Mishra , Paul Magron , Romain Serizel

2026

Pré-publication, Document de travail hal-05443978v1
Deposit thumbnail

Domain-Invariant Representation Learning of Bird Sounds

Ilyass Moummad , Romain Serizel , Emmanouil Benetos , Nicolas Farrugia

2024

Pré-publication, Document de travail hal-04696391v1
Deposit thumbnail

Latent Watermarking of Audio Generative Models

Robin San Roman , Pierre Fernandez , Antoine Deleforge , Yossi Adi , Romain Serizel

2024

Pré-publication, Document de travail hal-04716743v1
Deposit thumbnail

Energy Consumption Trends in Sound Event Detection Systems

Constance Douwes , Romain Serizel

2024

Pré-publication, Document de travail hal-04697014v1
Deposit thumbnail

Le comportement des systèmes de reconnaissance du locuteur de l'état de l'art face aux variabiliés acoustiques

Mohammad Mohammadamini , Driss Matrouf , Jean-François Bonatsre , Sandipana Dowerah , Romain Serizel et al.

2022

Pré-publication, Document de travail hal-03564767v1
Deposit thumbnail

Towards an efficient computation of masks for multichannel speech enhancement

Louis Delebecque , Romain Serizel , Nicolas Furnon

2022

Pré-publication, Document de travail hal-03604983v1

MULTICHANNEL SPEECH ENHANCEMENT FOR SPEAKER VERIFICATION IN NOISY AND REVERBERANT ENVIRONMENTS

Sandipana Dowerah , Romain Serizel , Denis Jouvet , Mohammad Mohammadamini , Driss Matrouf

2021

Pré-publication, Document de travail hal-03487420v1
Deposit thumbnail

SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays

Nicolas Furnon , Romain Serizel , Slim Essid , Irina Illina

2021

Pré-publication, Document de travail hal-04173974v1
Deposit thumbnail

Analysis of weak labels for sound event tagging

Nicolas Turpault , Romain Serizel , Emmanuel Vincent

2021

Pré-publication, Document de travail hal-03203692v1
Deposit thumbnail

The Speed Submission to DIHARD II: Contributions & Lessons Learned

Md Sahidullah , Jose Patino , Samuele Cornell , Ruiqing Yin , Sunit Sivasankaran et al.

2019

Pré-publication, Document de travail hal-02352840v2