SDASSep 26, 2021

Joint magnitude estimation and phase recovery using Cycle-in-Cycle GAN for non-parallel speech enhancement

arXiv:2109.12591v44 citations
Originality Incremental advance
AI Analysis

This addresses speech quality degradation in low signal-to-noise ratio conditions for applications like audio processing, though it is incremental as it builds on existing GAN methods.

The paper tackled the problem of non-parallel speech enhancement by jointly estimating spectral magnitude and phase using a Cycle-in-Cycle GAN, achieving significant performance improvements over baselines, especially in reducing background noise and speech distortion.

For the lack of adequate paired noisy-clean speech corpus in many real scenarios, non-parallel training is a promising task for DNN-based speech enhancement methods. However, because of the severe mismatch between input and target speeches, many previous studies only focus on the magnitude spectrum estimation and remain the phase unaltered, resulting in the degraded speech quality under low signal-to-noise ratio conditions. To tackle this problem, we decouple the difficult target w.r.t. original spectrum optimization into spectral magnitude and phase, and a novel Cycle-in-Cycle generative adversarial network (dubbed CinCGAN) is proposed to jointly estimate the spectral magnitude and phase information stage by stage under unpaired data. In the first stage, we pretrain a magnitude CycleGAN to coarsely estimate the spectral magnitude of clean speech. In the second stage, we incorporate the pretrained CycleGAN with a complex-valued CycleGAN as a cycle-in-cycle structure to simultaneously recover phase information and refine the overall spectrum. Experimental results demonstrate that the proposed approach significantly outperforms previous baselines under non-parallel training. The evaluation on training the models with standard paired data also shows that CinCGAN achieves remarkable performance especially in reducing background noise and speech distortion.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes