paper-with-me

홈 › Papers

Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training

2025-09-25 · Naisong Zhou, Saisamarth Rajesh Phaye, Milos Cernak, Tijana Stojkovic, Andy Pearce, Andrea Cavallaro, Andy Harper arxiv

Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Neural Function Evaluations (NFEs), posing a challenge for real-time applications. On the contrary, flow matching offers a more efficient alternative by learning a direct vector field, enabling high-quality synthesis in just a few steps using deterministic ordinary differential equation~(ODE) solvers. We thus introduce Shortcut Flow Matching for Speech Enhancement (SFMSE), a novel approach that trains a single, step-invariant model. By conditioning the velocity field on the target time step during a one-stage training process, SFMSE can perform single, few, or multi-step denoising without any architectural changes or fine-tuning. Our results demonstrate that a single-step SFMSE inference achieves a real-time factor (RTF) of 0.013 on a consumer GPU while delivering perceptual quality comparable to a strong diffusion baseline requiring 60 NFEs. This work also provides an empirical analysis of the role of stochasticity in training and inference, bridging the gap between high-quality generative SE and low-latency constraints.

📄 PDF Abstract BibTeX arXiv:2509.21522

Code (0)

등록된 구현이 없습니다.

Tasks

Speech 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

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

2025-09-19 · Gang Yang, Yue Lei, Wenxin Tai, Jin Wu 외 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. Re…

Speech Enhancement

GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling

2025-01-31 · Pinxin Liu, Luchuan Song, Junhua Huang, Haiyang Liu 외

Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body regions such as body, legs and hands separately, which fail to capture the spa…

DenoisingGesture Generation

Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

2026-06-23 · Wangyi Pu, Michele Scarpiniti arxiv

Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment. Flow Matching offer…

Speech Enhancement

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

2025-10-15 · Xu Cai, Yang Wu, Qianli Chen, Haoran Wu 외 arxiv

We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortc…