用直线概率路径提升语音增强质量，训练更稳效果更好。
Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement
- 采用条件流匹配构建从噪声到清晰语音的直线概率路径。
- 时间无关方差对生成质量影响大于梯度，且单步推理即可完成。
- 适合追求高音质、低延迟的语音增强应用。
当前基于流的语音增强方法学习的是弯曲的概率路径，建模了干净语音与噪声语音之间的映射关系。尽管性能出色，但弯曲路径的实际影响尚不明确。如薛定谔桥这类方法专注于弯曲路径，其时变梯度和方差不利于生成直线路径。机器学习研究指出，直线路径（如条件流匹配）更易训练且泛化能力更强。本文量化分析了路径直度对语音增强质量的影响，实验表明某些配置下薛定谔桥可生成更直路径。为此，我们提出独立的条件流匹配用于语音增强，直接建模噪声到干净语音的直线路径。实验证明，时间无关方差对样本质量的影响超过梯度。虽然条件流匹配提升了多个语音质量指标，但需多步推理。我们通过将训练好的流模型当作直接预测器，实现单步推理。结果表明，更直的、时间无关的概率路径在生成式语音增强上优于弯曲的时间相关路径。
原文摘要 · Abstract (English)
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 are unknown. Methods such as Schrodinger bridges focus on curved paths, where time-dependent gradients and variance do not promote straight paths. Findings in machine learning research suggest that straight paths, such as conditional flow matching, are easier to train and offer better generalisation. In this paper we quantify the effect of path straightness on speech enhancement quality. We report experiments with the Schrodinger bridge, where we show that certain configurations lead to straighter paths. Conversely, we propose independent conditional flow-matching for speech enhancement, which models straight paths between noisy and clean speech. We demonstrate empirically that a time-independent variance has a greater effect on sample quality than the gradient. Although conditional flow matching improves several speech quality metrics, it requires multiple inference steps. We rectify this with a one-step solution by inferring the trained flow-based model as if it was directly predictive. Our work suggests that straighter time-independent probability paths improve generative speech enhancement over curved time-dependent paths.
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。