SDLGASFeb 3, 2021

Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses

arXiv:2102.01993v255 citationsHas Code
AI Analysis

This work offers an incremental improvement to existing speech enhancement models by enhancing feature representation and optimizing with a mixed loss function.

This paper proposes a complex convolutional block attention module (CCBAM) and a joint time-frequency loss function to improve monaural speech enhancement. By integrating these components into existing deep complex U-Net and CRN architectures, the authors achieve superior performance in objective evaluations.

Deep complex U-Net structure and convolutional recurrent network (CRN) structure achieve state-of-the-art performance for monaural speech enhancement. Both deep complex U-Net and CRN are encoder and decoder structures with skip connections, which heavily rely on the representation power of the complex-valued convolutional layers. In this paper, we propose a complex convolutional block attention module (CCBAM) to boost the representation power of the complex-valued convolutional layers by constructing more informative features. The CCBAM is a lightweight and general module which can be easily integrated into any complex-valued convolutional layers. We integrate CCBAM with the deep complex U-Net and CRN to enhance their performance for speech enhancement. We further propose a mixed loss function to jointly optimize the complex models in both time-frequency (TF) domain and time domain. By integrating CCBAM and the mixed loss, we form a new end-to-end (E2E) complex speech enhancement framework. Ablation experiments and objective evaluations show the superior performance of the proposed approaches (https://github.com/modelscope/ClearerVoice-Studio).

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes