arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.18355eess.AS
收藏

重新思考流与扩散桥模型用于语音增强

Rethinking Flow and Diffusion Bridge Models for Speech Enhancement

Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University(南京大学声学研究所现代声学重点实验室);NJU-Horizon Intelligent Audio Lab, Horizon Robotics(地平线智能音频实验室);Tencent AI Lab(腾讯AI实验室)

Dahan Wang, Jun Gao, Tong Lei, Yuxiang Hu, Changbao Zhu, Kai Chen, Jing Lu

AI总结:

本文提出了一种统一流与扩散桥模型的框架,通过改进的概率路径设计和预测范式元素,提升了语音增强的性能和效率。

摘要:

流匹配和扩散桥模型已成为生成语音增强中的主流范式,其通过基于流匹配、分数匹配和Schrödinger桥等原理,建模配对的噪声和干净语音信号之间的随机过程。在本文中,我们提出了一种框架,通过将现有流和扩散桥模型解释为具有不同均值和方差的高斯概率路径构造,将它们统一起来。此外,我们研究了这些生成模型与传统预测模型的训练/推理过程之间的内在一致性。我们的分析表明,每个经过数据预测损失优化的流或扩散桥模型的采样步骤在理论上等同于执行预测语音增强。受这一见解的启发,我们引入了一个增强的桥模型,该模型整合了有效的概率路径设计与来自预测范式的关键元素,包括改进的网络架构、定制的损失函数和优化的训练策略。在去噪和去回声任务上的实验表明,所提出的方法在参数更少和计算复杂性更低的情况下优于现有的流和扩散基线。结果还表明,这种生成框架固有的预测性质对其可实现的上界性能施加了限制。

英文摘要:

Flow matching and diffusion bridge models have emerged as leading paradigms in generative speech enhancement, modeling stochastic processes between paired noisy and clean speech signals based on principles such as flow matching, score matching, and Schrödinger bridge. In this paper, we present a framework that unifies existing flow and diffusion bridge models by interpreting them as constructions of Gaussian probability paths with varying means and variances between paired data. Furthermore, we investigate the underlying consistency between the training/inference procedures of these generative models and conventional predictive models. Our analysis reveals that each sampling step of a well-trained flow or diffusion bridge model optimized with a data prediction loss is theoretically analogous to executing predictive speech enhancement. Motivated by this insight, we introduce an enhanced bridge model that integrates an effective probability path design with key elements from predictive paradigms, including improved network architecture, tailored loss functions, and optimized training strategies. Experiments on denoising and dereverberation tasks demonstrate that the proposed method outperforms existing flow and diffusion baselines with fewer parameters and reduced computational complexity. The results also highlight that the inherently predictive nature of this generative framework imposes limitations on its achievable upper-bound performance.

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。

↑