Jean-Marie Lemercier

38 papers A* 2A 3Misc 5Journal 24Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Scaling Beyond Masked Diffusion Language Models.
CoRR
Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang, Justin Deschenaux, Jingyu Liu, John Thickstun, Ante Jukic
2025 Misc conf
HRTF Estimation using a Score-based Prior.
ICASSP
Etienne Thuillier, Jean-Marie Lemercier, Eloi Moliner, Timo Gerkmann, Vesa Välimäki
2025 A conf
Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech.
INTERSPEECH
Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann
2024 A* conf
An Independence-promoting Loss for Music Generation with Language Models.
ICML
Jean-Marie Lemercier, Simon Rouard, Jade Copet, Yossi Adi, Alexandre Défossez
2024 J jnl
An Independence-promoting Loss for Music Generation with Language Models.
CoRR
Jean-Marie Lemercier, Simon Rouard, Jade Copet, Yossi Adi, Alexandre Défossez
2024 — conf
BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models.
IWAENC
Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki
2024 J jnl
BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models.
CoRR
Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki
2024 J jnl
Diffusion Models for Audio Restoration.
CoRR
Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, Vesa Välimäki, Timo Gerkmann
2024 J jnl
Diffusion Models for Audio Restoration: A review [Special Issue On Model-Based and Data-Driven Audio Signal Processing].
IEEE Signal Process. Mag.
Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, Vesa Välimäki, Timo Gerkmann
2024 J jnl
HRTF Estimation using a Score-based Prior.
CoRR
Etienne Thuillier, Jean-Marie Lemercier, Eloi Moliner, Timo Gerkmann, Vesa Välimäki
2024 — conf
Meta-Learning For Variable Array Configurations in End-to-End Few-Shot Multichannel Speech Enhancement.
IWAENC
Alina Mannanova, Kristina Tesch, Jean-Marie Lemercier, Timo Gerkmann
2024 J jnl
Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech.
CoRR
Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann
2024 Misc conf
Single and Few-Step Diffusion for Generative Speech Enhancement.
ICASSP
Bunlong Lay, Jean-Marie Lemercier, Julius Richter, Timo Gerkmann
2024 J jnl
Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models.
CoRR
Jean-Marie Lemercier, Eloi Moliner, Simon Welker, Vesa Välimäki, Timo Gerkmann
2023 J jnl
A neural network-supported two-stage algorithm for lightweight dereverberation on hearing devices.
EURASIP J. Audio Speech Music. Process.
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2023 Misc conf
Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches for Speech Restoration.
ICASSP
Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann
2023 — conf
Diffusion Posterior Sampling for Informed Single-Channel Dereverberation.
WASPAA
Jean-Marie Lemercier, Simon Welker, Timo Gerkmann
2023 J jnl
Diffusion Posterior Sampling for Informed Single-Channel Dereverberation.
CoRR
Jean-Marie Lemercier, Simon Welker, Timo Gerkmann
2023 A conf
Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation.
INTERSPEECH
Jean-Marie Lemercier, Julian Tobergte, Timo Gerkmann
2023 J jnl
Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation.
CoRR
Jean-Marie Lemercier, Julian Tobergte, Timo Gerkmann
2023 J jnl
On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings.
CoRR
Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Tal Peer, Timo Gerkmann
2023 J jnl
Single and Few-step Diffusion for Generative Speech Enhancement.
CoRR
Bunlong Lay, Jean-Marie Lemercier, Julius Richter, Timo Gerkmann
2023 J jnl
Speech Enhancement and Dereverberation With Diffusion-Based Generative Models.
IEEE ACM Trans. Audio Speech Lang. Process.
Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann
2023 Misc conf
Speech Signal Improvement Using Causal Generative Diffusion Models.
ICASSP
Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Tal Peer, Timo Gerkmann
2023 J jnl
Speech Signal Improvement Using Causal Generative Diffusion Models.
CoRR
Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Tal Peer, Timo Gerkmann
2023 J jnl
StoRM: A Diffusion-Based Stochastic Regeneration Model for Speech Enhancement and Dereverberation.
IEEE ACM Trans. Audio Speech Lang. Process.
Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann
2023 J jnl
Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Model.
CoRR
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2022 J jnl
Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration.
CoRR
Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann
2022 Misc conf
Customizable End-To-End Optimization Of Online Neural Network-Supported Dereverberation For Hearing Devices.
ICASSP
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2022 J jnl
Customizable End-to-end Optimization of Online Neural Network-supported Dereverberation for Hearing Devices.
CoRR
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2022 J jnl
End-To-End Optimization of Online Neural Network-supported Two-Stage Dereverberation for Hearing Devices.
CoRR
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2022 A conf
Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments.
INTERSPEECH
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2022 J jnl
Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments.
CoRR
Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann
2022 J jnl
Speech Enhancement and Dereverberation with Diffusion-based Generative Models.
CoRR
Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann
2022 J jnl
StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation.
CoRR
Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann
2021 — conf
An Integrated Deep Clustering-Based System for Speaker Count Agnostic Speech Separation.
ITG Conference on Speech Communication
Jean-Marie Lemercier, Leroy Bartel, David Ditter, Timo Gerkmann
2021 A* conf
Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network.
NeurIPS
Xiaolin Hu, Kai Li, Weiyi Zhang, Yi Luo, Jean-Marie Lemercier, Timo Gerkmann
2021 J jnl
Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network.
CoRR
Xiaolin Hu, Kai Li, Weiyi Zhang, Yi Luo, Jean-Marie Lemercier, Timo Gerkmann