Deep Interaction between Masking and Mapping Targets for Single-Channel Speech Enhancement
This work addresses speech enhancement for noisy audio signals, offering an incremental improvement by integrating phase enhancement and computational efficiency.
The paper tackles the problem of single-channel speech enhancement by proposing a multi-branch dilated convolutional network that simultaneously enhances magnitude and phase, achieving better speech quality and intelligibility with less computation compared to state-of-the-art models.
The most recent deep neural network (DNN) models exhibit impressive denoising performance in the time-frequency (T-F) magnitude domain. However, the phase is also a critical component of the speech signal that is easily overlooked. In this paper, we propose a multi-branch dilated convolutional network (DCN) to simultaneously enhance the magnitude and phase of noisy speech. A causal and robust monaural speech enhancement system is achieved based on the multi-objective learning framework of the complex spectrum and the ideal ratio mask (IRM) targets. In the process of joint learning, the intermediate estimation of IRM targets is used as a way of generating feature attention factors to realize the information interaction between the two targets. Moreover, the proposed multi-scale dilated convolution enables the DCN model to have a more efficient temporal modeling capability. Experimental results show that compared with other state-of-the-art models, this model achieves better speech quality and intelligibility with less computation.