paper-with-me

홈 › Papers

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement

2025-08-20 · Bin Wen, Tien-Ping Tan arxiv

We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse acoustic features efficiently. An enhanced attention mechanism with dual normalization and residual refinement further improves training stability and convergence. Additionally, dynamic pruning is applied to reduce model size while maintaining performance, making the framework suitable for resource-constrained environments. Experimental evaluation on the public VoiceBank+DEMAND dataset shows that EffiFusion-GAN achieves a PESQ score of 3.45, outperforming existing models under the same parameter settings.

📄 PDF Abstract BibTeX arXiv:2508.14525

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Enhancement

Results from the Paper

RankTaskDatasetModelMetrics
#4 Speech Enhancement DEMAND EffiFusion-GAN PESQ: 3.45
#5 Speech Enhancement VoiceBank+DEMAND EffiFusion-GAN PESQ: 3.45

Similar Papers 제목 키워드 기반

VSEGAN: Visual Speech Enhancement Generative Adversarial Network

2021-02-04 · Xinmeng Xu, Yang Wang, Dongxiang Xu, Yiyuan Peng 외

Speech enhancement is an essential task of improving speech quality in noise scenario. Several state-of-the-art approaches have introduced visual information for speech enhancement,since the visual aspect of speech is es…

Generative Adversarial NetworkSpeech Enhancement

Universal Score-based Speech Enhancement with High Content Preservation

2024-06-18 · Robin Scheibler, Yusuke Fujita, Yuma Shirahata, Tatsuya Komatsu

We propose UNIVERSE++, a universal speech enhancement method based on score-based diffusion and adversarial training. Specifically, we improve the existing UNIVERSE model that decouples clean speech feature extraction an…

Speech Enhancement

FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks

2025-03-17 · Tong Lei, Qinwen Hu, Ziyao Lin, Andong Li 외

The prevailing method for neural speech enhancement predominantly utilizes fully-supervised deep learning with simulated pairs of far-field noisy-reverberant speech and clean speech. Nonetheless, these models frequently …

Speech Enhancement

Unsupervised speech enhancement with diffusion-based generative models

2023-09-19 · Berné Nortier, Mostafa Sadeghi, Romain Serizel

Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when g…

Speech Enhancement

A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI

2023-03-23 · Chenshuang Zhang, Chaoning Zhang, Sheng Zheng, Mengchun Zhang 외

Generative AI has demonstrated impressive performance in various fields, among which speech synthesis is an interesting direction. With the diffusion model as the most popular generative model, numerous works have attemp…

Speech EnhancementSpeech SynthesisSurveytext-to-speech+2