paper-with-me

홈 › Papers

Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement

2025-09-19 · Gang Yang, Yue Lei, Wenxin Tai, Jin Wu, Jia Chen, Ting Zhong, Fan Zhou arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.15952

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Enhancement

Similar Papers 제목 키워드 기반

Variational Rectified Flow Matching

2025-02-13 · Pengsheng Guo, Alexander G. Schwing

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

2025-05-30 · Md Shahriar Rahim Siddiqui, Moshe Eliasof, Eldad Haber

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 Generation

Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

2025-12-01 · Mudit Gaur, Prashant Trivedi, Shuchin Aeron, Amrit Singh Bedi 외 arxiv

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

2026-05-21 · Shengzhe Chen, Mehrdad Moradi, Kamran Paynabar, Hao Yan arxiv

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 Detection

Riemannian MeanFlow for One-Step Generation on Manifolds

2026-03-11 · Zichen Zhong, Haoliang Sun, Yukun Zhao, Yongshun Gong 외 arxiv

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