论文标题
具有动态关注单声道语音增强的递归网络
A Recursive Network with Dynamic Attention for Monaural Speech Enhancement
论文作者
论文摘要
一个人倾向于在复杂的环境下引起对语音的动态关注。基于这种现象，我们提出了一个将动态注意力和递归学习结合在一起以增强单声道的框架。除了主要减少降噪网络外，我们设计了一个分离的子网络，该子网络可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，引入了递归学习，这意味着该网络已在多个阶段重复使用，其中每个阶段的中间输出与存储机构相关。结果，可以获得更灵活，更好的估计。我们在timit语料库上进行实验。实验结果表明，就PESQ和Stoi分数而言，所提出的架构比最近的最新模型始终取得更好的性能。
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.
