{"ID":5551901,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T01:45:22.703757252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00363","arxiv_id":"2607.00363","title":"Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis","abstract":"Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we propose a unified guidance framework that enhances generation efficiency and robustness through two complementary strategies. On the data front, we introduce Data-guidance via heterogeneous augmentation, encouraging the model to disentangle linguistic content from acoustic residue. In parallel, we propose an enhanced Model-guidance mechanism that synergizes trajectory rectification with a novel intrinsic guidance objective. This approach distills conditional knowledge into network weights and straightens inference trajectory path, thereby eliminating Classifier-Free Guidance (CFG) overhead. Experiments demonstrate that our framework accelerates inference by nearly three times while effectively improving speaker similarity compared to state-of-the-art baselines.","short_abstract":"Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we propose a unified guidance framework that enhances generation efficiency and robustness through two complementary strategies. On the data fro...","url_abs":"https://arxiv.org/abs/2607.00363","url_pdf":"https://arxiv.org/pdf/2607.00363v1","authors":"[\"Zuda Yu\",\"Qianhui Xu\",\"Ting Chen\",\"Junhui Zhang\",\"Tao Fu\",\"Hongjiang Yu\",\"Qiangqing Wang\",\"Yang Song\"]","published":"2026-07-01T03:02:31Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\"]","methods":"[]","has_code":false}