Speech Enhancement Based on CycleGAN with Noise-informed Training
- Resource Type
- Conference
- Authors
- Ting, Wen-Yuan; Wang, Syu-Siang; Chang, Hsin-Li; Su, Borching; Tsao, Yu
- 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
- Computing and Processing
Signal Processing and Analysis
Training
Training data
Speech enhancement
Generative adversarial networks
Generators
Noise measurement
Task analysis
speech enhancement
weakly supervised learning
CycleGAN
neural network
noise identity
- Language
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.