A Speech Enhancement Method Using Attention Mechanism and Gated Recurrent Unit

Abstract

Noise has great harm to speech. Therefore, speech enhancement plays a vital role in speech signal processing. To further improve the effect of speech enhancement, a speech enhancement method based on a gated recurrent unit with an attention mechanism (AGRU) is proposed. Firstly, the attention mechanism is used to extract important features in the speech signals. Then the gated recurrent unit (GRU) is used to map the complex relationship between noisy speech and pure speech. The collected speeches of different emotions are used for simulation. The results show that the method proposed in this paper can remove speech noise and is better than other methods. The method proposed in this paper can provide some references for the application of deep learning in speech enhancement.