Dynamic Attention Based Generative Adversarial Network With Phase Post-processing For Speech Enhancement
2020 · Andong Li, Chengshi Zheng, Renhua Peng, et al.
Abstract
The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a powerful Dynamic Attention Recursive GAN called DARGAN for noise reduction in the time-frequency domain. Different from previous works, we have several innovations. First, recursive learning, an iterative training protocol, is used in the generator, which consists of multiple steps. By reusing the network in each step, the noise components are progressively reduced in a step-wise manner. Second, the dynamic attention mechanism is deployed, which helps to re-adjust the feature distribution in the noise reduction module. Third, we exploit the deep Griffin-Lim algorithm as the module for phase postprocessing, which facilitates further improvement in speech quality. Experimental results on Voice Bank corpus show that the proposed GAN achieves state-of-the-a
Authors
(none)
Tags
Stats
Related papers
- DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network For Speech Enhancement (2020)0.00
- Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
- Investigating Generative Adversarial Networks Based Speech Dereverberation For Robust Speech Recognition (2018)10.74
- SEGAN: Speech Enhancement Generative Adversarial Network (2017)21.85
- Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network For End-to-end Speech Enhancement (2020)0.00
- Exploring Speech Enhancement With Generative Adversarial Networks For Robust Speech Recognition (2017)16.14
- Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
- Boosting Noise Robustness Of Acoustic Model Via Deep Adversarial Training (2018)9.23