Cover Image

Do We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network Architecture

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Richter, Julius, de Oliveira, Danilo, Gerkmann, Timo
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Investigating Training Objectives for Generative Speech Enhancement
by: Richter, Julius, et al.
Published: (2024)

LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models
by: Richter, Julius, et al.
Published: (2025)

The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement
by: de Oliveira, Danilo, et al.
Published: (2024)

Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech
by: de Oliveira, Danilo, et al.
Published: (2024)

StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
by: Lemercier, Jean-Marie, et al.
Published: (2022)

Speech Enhancement and Dereverberation with Diffusion-based Generative Models
by: Richter, Julius, et al.
Published: (2022)

An Analysis of the Variance of Diffusion-based Speech Enhancement
by: Lay, Bunlong, et al.
Published: (2024)

Single and Few-step Diffusion for Generative Speech Enhancement
by: Lay, Bunlong, et al.
Published: (2023)

ReverbFX: A Dataset of Room Impulse Responses Derived from Reverb Effect Plugins for Singing Voice Dereverberation
by: Richter, Julius, et al.
Published: (2025)

Are These Even Words? Quantifying the Gibberishness of Generative Speech Models
by: de Oliveira, Danilo, et al.
Published: (2025)

Bone-conduction Guided Multimodal Speech Enhancement with Conditional Diffusion Models
by: Khanagha, Sina, et al.
Published: (2026)

Diffusion Buffer for Online Generative Speech Enhancement
by: Lay, Bunlong, et al.
Published: (2025)

EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
by: Richter, Julius, et al.
Published: (2024)

Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
by: Makarov, Rostislav, et al.
Published: (2025)

Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters
by: Tesch, Kristina, et al.
Published: (2023)

Diffusion Models for Audio Restoration
by: Lemercier, Jean-Marie, et al.
Published: (2024)

Too Good to Be True: A Study on Modern Automatic Speech Recognition for the Evaluation of Speech Enhancement
by: de Oliveira, Danilo, et al.
Published: (2026)

EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Data
by: Prabhu, Navin Raj, et al.
Published: (2023)

Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech
by: de Groot, Dimme, et al.
Published: (2025)

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
by: Lu, Ye-Xin, et al.
Published: (2023)

Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
by: Kienegger, Jakob, et al.
Published: (2025)

Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
by: Kienegger, Jakob, et al.
Published: (2026)

Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios
by: Kienegger, Jakob, et al.
Published: (2026)

A Lightweight Fourier-based Network for Binaural Speech Enhancement with Spatial Cue Preservation
by: Lu, Xikun, et al.
Published: (2025)

Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Model
by: Lemercier, Jean-Marie, et al.
Published: (2023)

Absorbing Discrete Diffusion for Speech Enhancement
by: Gonzalez, Philippe
Published: (2026)

Universal Score-based Speech Enhancement with High Content Preservation
by: Scheibler, Robin, et al.
Published: (2024)

An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement
by: Ku, Pin-Jui, et al.
Published: (2024)

Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning
by: Zhao, Shengkui, et al.
Published: (2025)

Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement
by: Zhao, Haixin, et al.
Published: (2025)

Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation
by: Kienegger, Jakob, et al.
Published: (2024)

Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired by Dynamic Neural Network
by: Chen, Yanan, et al.
Published: (2024)

Diffusion-based Signal Refiner for Speech Enhancement and Separation
by: Hirano, Masato, et al.
Published: (2023)

Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement
by: Huang, Ziling, et al.
Published: (2025)

Combining Deterministic Enhanced Conditions with Dual-Streaming Encoding for Diffusion-Based Speech Enhancement
by: Shi, Hao, et al.
Published: (2025)

Towards Environmental Preference Based Speech Enhancement For Individualised Multi-Modal Hearing Aids
by: Kirton-Wingate, Jasper, et al.
Published: (2024)

Robust Speech Recognition with Schrödinger Bridge-Based Speech Enhancement
by: Nasretdinov, Rauf, et al.
Published: (2025)

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement
by: Li, Yi, et al.
Published: (2024)

BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models
by: Moliner, Eloi, et al.
Published: (2024)

Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models
by: Lemercier, Jean-Marie, et al.
Published: (2024)