paper-with-me

홈 › Papers

MeanFlowSE: one-step generative speech enhancement via conditional mean flow

2025-09-18 · Duojia Li, Shenghui Lu, Hongchen Pan, Zongyi Zhan, Qingyang Hong, Lin Li arxiv

Multistep inference is a bottleneck for real-time generative speech enhancement because flow- and diffusion-based systems learn an instantaneous velocity field and therefore rely on iterative ordinary differential equation (ODE) solvers. We introduce MeanFlowSE, a conditional generative model that learns the average velocity over finite intervals along a trajectory. Using a Jacobian-vector product (JVP) to instantiate the MeanFlow identity, we derive a local training objective that directly supervises finite-interval displacement while remaining consistent with the instantaneous-field constraint on the diagonal. At inference, MeanFlowSE performs single-step generation via a backward-in-time displacement, removing the need for multistep solvers; an optional few-step variant offers additional refinement. On VoiceBank-DEMAND, the single-step model achieves strong intelligibility, fidelity, and perceptual quality with substantially lower computational cost than multistep baselines. The method requires no knowledge distillation or external teachers, providing an efficient, high-fidelity framework for real-time generative speech enhancement. The proposed method is open-sourced at https://github.com/liduojia1/MeanFlowSE.

📄 PDF Abstract BibTeX arXiv:2509.14858

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationSpeech Enhancement

Similar Papers 제목 키워드 기반

Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement

2025-08-28 · Mattias Cross, Anton Ragni arxiv

Current flow-based generative speech enhancement methods learn curved probability paths which model a mapping between clean and noisy speech. Despite impressive performance, the implications of curved probability paths a…

Speech Enhancement

Speech Enhancement Based on Drifting Models

2026-04-27 · Liang Xu, Diego Caviedes-Nozal, W. Bastiaan Kleijn, Longfei Felix Yan 외 arxiv

We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Rather than relying on iterative sampling, DriftSE natively achieves one…

Speech Enhancement

Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders

2019-08-07 · Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin 외

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech sign…

Speech Enhancement

Investigating the Effects of Diffusion-based Conditional Generative Speech Models Used for Speech Enhancement on Dysarthric Speech

2024-12-18 · Joanna Reszka, Parvaneh Janbakhshi, Tilak Purohit, Sadegh Mohammadi

In this study, we aim to explore the effect of pre-trained conditional generative speech models for the first time on dysarthric speech due to Parkinson's disease recorded in an ideal/non-noisy condition. Considering one…

Speech Enhancement

Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain

2022-03-31 · Simon Welker, Julius Richter, Timo Gerkmann

Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend…

Speech Enhancement