학술논문
Speech Enhancement Based on CycleGAN with Noise-informed Training
Document Type
Conference
Source
2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP) Chinese Spoken Language Processing (ISCSLP), 2022 13th International Symposium on. :155-159 Dec, 2022
Subject
Language
Abstract
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-t0-clean and cleant0-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-t0-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.