# Speech Enhancement Based on Cyclegan with Noise-informed Training

arXiv: https://arxiv.org/abs/2110.09924 · HTML: https://mlsanity.com/paper/2110.09924/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2021.

## Built on by (most cited first, 1 of 1)

- [SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model](https://mlsanity.com/paper/2411.07751/) (2024)

## Abstract (arXiv)

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.