用薛定谔桥直接建模降噪过程，低信噪比下效果更优。
Diffusion-based Speech Enhancement with Schrödinger Bridge and Symmetric Noise Schedule
- 直接学习噪声到干净语音的扩散路径，不经过高斯分布
- 低信噪比下性能超越所有基线模型，仅需少数推理步数
- 适合对极低信噪比语音增强有需求的研究与应用
近期基于扩散模型的语音增强方法表现出色，但仍面临结构信息缺失和低信噪比（SNR）场景性能不佳的问题。为此，本文提出基于薛定谔桥的语音增强方法（SBSE），直接学习噪声输入与干净语音分布之间的扩散过程，不同于传统方法将数据映射至高斯分布。为提升极端嘈杂条件下的表现，引入两阶段系统，将比率掩码信息融入扩散生成模型。实验结果表明，所提方法在所有基线模型中表现最优，尤其在低SNR条件下优势显著，且仅需少量推理步骤即可达到最佳效果。
原文摘要 · Abstract (English)
Recently, diffusion-based generative models have demonstrated remarkable performance in speech enhancement tasks. However, these methods still encounter challenges, including the lack of structural information and poor performance in low Signal-to-Noise Ratio (SNR) scenarios. To overcome these challenges, we propose the Schröodinger Bridge-based Speech Enhancement (SBSE) method, which learns the diffusion processes directly between the noisy input and the clean distribution, unlike conventional diffusion-based speech enhancement systems that learn data to Gaussian distributions. To enhance performance in extremely noisy conditions, we introduce a two-stage system incorporating ratio mask information into the diffusion-based generative model. Our experimental results show that our proposed SBSE method outperforms all the baseline models and achieves state-of-the-art performance, especially in low SNR conditions. Importantly, only a few inference steps are required to achieve the best result.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。