Speech Dereverberation

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Prox-Friendly Log-Magnitude Prior on Complex-Valued Signal
Sep 28, 2026Kazuki Matsumoto, Keidai Arai, Kohei YatabeSpectral Regularization Speech Enhancement
Tokyo University of Agriculture and Technology (TUAT), Tokyo, Japan
DriftSE: Speech Enhancement with Generative Drifting
Sep 10, 2026Liang Xu, Diego Caviedes-Nozal, W. Bastiaan Kleijn +2One-Step Generative Modeling Speech Enhancement
Victoria University of Wellington, New Zealand · GN Advanced Science, Denmark · Lincoln University
LipsAM: Lipschitz-continuous Neural Networks for Convergent Plug-and-Play Audio Signal Recovery
Aug 24, 2026Kazuki Matsumoto, Ren Uchida, Natsuki Yoshino +1Speech Dereverberation Lipschitz Neural Networks
Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan
A Cold Diffusion Approach for Percussive Dereverberation
May 11, 2026Dimos Makris, András Barják, Maximos Kaliakatsos-PapakostasAudio Diffusion Models Speech Dereverberation
Department of Music Technology and Acoustics Hellenic Mediterranean University Rethymno, Greece · XLN Audio Stockholm, Sweden
MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation
May 1, 2026Akira Takahashi, Ryosuke Sawata, Shusuke Takahashi +1Room Acoustics Speech Dereverberation
Sony Group Corporation · Sony AI
LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation
Mar 23, 2026Kazuki Matsumoto, Ren Uchida, Kohei YatabeSpeech Dereverberation Lipschitz Neural Networks
Tokyo University of Agriculture and Technology, Tokyo, Japan
StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement
Mar 10, 2026Xiaobin Rong, Jun Gao, Zheng Wang +3Speech Dereverberation Speech Enhancement
Key Laboratory of Modern Acoustics, Nanjing University · Collaboration AI, Cisco Systems, Inc. · NJU-Horizon Intelligent Audio Lab, Horizon Robotics
Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement
Mar 3, 2026Szu-Wei Fu, Rong Chao, Xuesong Yang +6Speech Enhancement Distortion-Perception Tradeoff
NVIDIA · Academia Sinica, Taipei, Taiwan

Sep 28, 2026J/K move · Enter open · S save

Prox-Friendly Log-Magnitude Prior on Complex-Valued Signal

Kazuki Matsumoto, Keidai Arai, Kohei Yatabe

Tokyo University of Agriculture and Technology (TUAT), Tokyo, Japan

Spectral Regularization Speech Enhancement Speech Dereverberation

Open paper AskPDF arXiv

The logarithmic transform is essential in audio signal processing since human auditory perception is approximately logarithmic with respect to magnitude. However, directly incorporating prior knowledge about signals (e.g., harmonic structure) in the log-magnitude domain into optimization problems solved by standard proximal splitting algorithms remains challenging. To address this issue, this paper proposes a novel regularizer termed EPILOG (Exponential Penalty for Imposing priors on LOG-magnitude). EPILOG indirectly imposes prior knowledge on the log-magnitude of a complex-valued signal through regularization of an auxiliary variable that is shown to be linked with the log-magnitude. Furthermore, we derive its variable-wise proximity operators and develop a proximal splitting algorithm using these operators. Experiments on speech dereverberation demonstrate the effectiveness of the proposed regularizer, particularly in promoting cepstral-domain sparsity.