Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement
Diffusion and flow matching (FM) models have achieved remarkable progress in speech enhancement (SE), yet their dependence on multi-step generation is computationally expensive and vulnerable to discretization errors. Recent advances in one-step generative modeling, particularly MeanFlow, provide a promising alternative by reformulating dynamics through average velocity fields. In this work, we present COSE, a one-step FM framework tailored for SE. To address the high training overhead of Jacobian-vector product (JVP) computations in MeanFlow, we introduce a velocity composition identity to compute average velocity efficiently, eliminating expensive computation while preserving theoretical consistency and achieving competitive enhancement quality. Extensive experiments on standard benchmarks show that COSE delivers up to 5x faster sampling and reduces training cost by 40%, all without compromising speech quality. Code is available at https://github.com/ICDM-UESTC/COSE.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech EnhancementSimilar Papers 제목 키워드 기반
Variational Rectified Flow Matching
We study Variational Rectified Flow Matching, a framework that enhances classic rectified flow matching by modeling multi-modal velocity vector-fields. At inference time, classic rectified flow matching 'moves' samples f…
Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields
Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only it…
Image GenerationGenerative Modeling with Continuous Flows: Sample Complexity of Flow Matching
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. …
Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
We propose Flow Mismatching, an unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms. Instead, we treat flow matching as geometric dynamics and leverage a key insight: anomalies o…
Unsupervised Anomaly DetectionRiemannian MeanFlow for One-Step Generation on Manifolds
Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE. We propose Riemannian MeanFlow (RMF), ex…
Multi-Task Learning