Cycle-consistent generative adversarial networks (CycleGAN) were successfully applied to speech enhancement (SE) tasks with unpaired noisy-clean training data. The CycleGAN SE system adopted two generators and two discriminators trained with losses from noisy-to-clean and clean-to-noisy conversions. CycleGAN showed promising results for numerous SE tasks. Herein, we investigate a potential limitation of the clean-to-noisy conversion part and propose a novel noise-informed training (NIT) approach to improve the performance of the original CycleGAN SE system. The main idea of the NIT approach is to incorporate target domain information for clean-to-noisy conversion to facilitate a better training procedure. The experimental results confirmed that the proposed NIT approach improved the generalization capability of the original CycleGAN SE system with a notable margin.

翻译：循环基因对抗网络(CycleGAN)成功地应用到语言增强任务(SE)中,没有噪音的吵闹清洁培训数据,循环GAN SE系统采用了两台发电机和两台歧视器,其损失来自噪音到清洁和清洁到噪音的转换。循环GAN为许多循环对抗网络任务展示了大有希望的结果。在这里,我们调查了清洁到噪音转换部分的潜在局限性,并提出了一种新的噪音意识培训(NIT)方法,以改进原循环GAN SE系统的性能。NIT方法的主要想法是纳入清洁到噪音转换的目标域信息,以促进更好的培训程序。实验结果证实,拟议的NIT方法提高了原循环GAN SE系统的普及能力,并具有显著的优势。