A person tends to generate dynamic attention towards speech under complicated environments. Based on this phenomenon, we propose a framework combining dynamic attention and recursive learning together for monaural speech enhancement. Apart from a major noise reduction network, we design a separated sub-network, which adaptively generates the attention distribution to control the information flow throughout the major network. To effectively decrease the number of trainable parameters, recursive learning is introduced, which means that the network is reused for multiple stages, where the intermediate output in each stage is correlated with a memory mechanism. As a result, a more flexible and better estimation can be obtained. We conduct experiments on TIMIT corpus. Experimental results show that the proposed architecture obtains consistently better performance than recent state-of-the-art models in terms of both PESQ and STOI scores.

中文翻译：

---

用于单耳语音增强的具有动态注意的递归网络

一个人倾向于在复杂环境下对语音产生动态注意。基于这种现象，我们提出了一个将动态注意力和递归学习相结合的框架，用于增强单声道语音。除了一个主要的降噪网络，我们还设计了一个分离的子网络，它自适应地生成注意力分布以控制整个主要网络的信息流。为了有效地减少可训练参数的数量，递归学习被引入，这意味着网络被重复用于多个阶段，其中每个阶段的中间输出与记忆机制相关。结果，可以获得更灵活和更好的估计。我们在 TIMIT 语料库上进行实验。