Deep neural network based speech enhancement technique focuses on learning a noisy-to-clean transformation supervised by paired training data. However, the task-specific evaluation metric (e.g., PESQ) is usually non-differentiable and can not be directly constructed in the training criteria. This mismatch between the training objective and evaluation metric likely results in sub-optimal performance. To alleviate it, we propose a metric-oriented speech enhancement method (MOSE), which leverages the recent advances in the diffusion probabilistic model and integrates a metric-oriented training strategy into its reverse process. Specifically, we design an actor-critic based framework that considers the evaluation metric as a posterior reward, thus guiding the reverse process to the metric-increasing direction. The experimental results demonstrate that MOSE obviously benefits from metric-oriented training and surpasses the generative baselines in terms of all evaluation metrics.

翻译：基于深度神经网络的语音增强技术侧重于通过配对训练数据监督学习从含噪到干净的转换。然而，任务特定的评估指标（如PESQ）通常不可微，无法直接纳入训练准则。这种训练目标与评估指标之间的不匹配可能导致次优性能。为解决这一问题，我们提出了一种面向指标的语音增强方法（MOSE），该方法利用扩散概率模型的最新进展，将面向指标的训练策略集成到其逆向过程中。具体而言，我们设计了一个基于演员-评论家（actor-critic）的框架，将评估指标视为后验奖励，从而引导逆向过程向指标提升方向优化。实验结果表明，MOSE显著受益于面向指标的训练，在所有评估指标上均超越了生成式基线方法。