增强流匹配：一种统一引导框架实现高效鲁棒的语音合成
Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis
AI总结：
针对流匹配语音合成中的高推理延迟和音色泄露问题，提出统一引导框架，通过数据引导（异构增强）和模型引导（轨迹整流与内在引导目标）提升效率与鲁棒性，实现近三倍加速并改善说话人相似度。
摘要：
流匹配（FM）已成为语音生成的一种强大范式，但仍受限于高推理延迟和音色泄露。为解决这些瓶颈，我们提出了一种统一引导框架，通过两种互补策略增强生成效率和鲁棒性。在数据方面，我们通过异构增强引入数据引导，鼓励模型将语言内容与声学残留分离。同时，我们提出了一种增强的模型引导机制，将轨迹整流与新颖的内在引导目标协同起来。该方法将条件知识蒸馏到网络权重中，并拉直推理轨迹路径，从而消除了无分类器引导（CFG）的开销。实验表明，与最先进的基线相比，我们的框架将推理速度提高了近三倍，同时有效改善了说话人相似度。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
