EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
This work addresses speech enhancement for resource-constrained environments, presenting an incremental improvement with efficiency gains.
The paper tackled speech enhancement by proposing EffiFusion-GAN, a lightweight model that integrates depthwise separable convolutions and an enhanced attention mechanism, achieving a PESQ score of 3.45 on the VoiceBank+DEMAND dataset.
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.