期刊论文

GAN Speech Enhancement Algorithm with Multi-stage Generator and Time-frequency Discriminator

中文

计算机系统应用

1003-3254

2022

31

7

179-185

10.3969/j.issn.1003-3254.2022.07.023

本校为其他机构

传统生成对抗网络的语音增强算法（SEGAN）将时域语音波形作为映射目标,在低信噪比条件下,语音时域波形会淹没在噪声中,导致SEGAN的增强性能会急剧下降,语音失真现象较为严重.针对该问题,提出了一种多阶段的时频域生成对抗网络的语音增强算法（multi-stage-time-frequency SEGAN, MS-TFSEGAN）. MS-TFSEGAN采用了多阶段生成器与时频域双鉴别器的模型结构,不断对映射结果进行完善,同时捕获时域与频域信息.另外,为了进一步提升模型对频域细节信息的学习能力, MS-TFSEGAN在生成器损失函数中引入了频域L1损失.实验证明,在低信噪比条件下, MS-TFSEGAN的语音质量和可懂度与SEGAN相比分别提升了约13.32...

The traditional speech enhancement generative adversarial network(SEGAN)takes the waveform of timedomain speech as the mapping target.When it comes to a low signal-to-noise ratio,the waveform of time-domain speech is drowned in the noise,resulting in a dramatic degradation of the enhancement performance of SEGAN and more serious speech distortion.In response,a multi-stage-time-frequency SEGAN(MS-TFSEGAN)is proposed for speech enhancement.MS-TFSEGAN employs multi-stage generators with dual time-frequency discriminators to continuously refine the mapping results.It captures both time-and frequen...