Self-attention Generative Adversarial Network For Speech Enhancement

Abstract

Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input. To remedy this issue, we propose a self-attention layer adapted from non-local attention, coupled with the convolutional and deconvolutional layers of a speech enhancement GAN (SEGAN) using raw signal input. Further, we empirically study the effect of placing the self-attention layer at the (de)convolutional layers with varying layer indices as well as at all of them when memory allows. Our experiments show that introducing self-attention to SEGAN leads to consistent improvement across the objective evaluation metrics of enhancement performance. Furthermore, applying at different (de)convolutional layers does not significantly alter performance, suggesting that it can be conveniently applied at the highest-level (de)convolutional layer with the smallest memory overhead.

Stats

• citations37
• S2 citations—
• github stars0
• HF likes0
• heat score11.85
• arxiv keyphan2020self

Related papers

• SEGAN: Speech Enhancement Generative Adversarial Network (2017)21.85
• Conditional Generative Adversarial Networks For Speech Enhancement And Noise-robust Speaker Verification (2017)16.03
• DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network For Speech Enhancement (2020)0.00
• Adversarial Joint Training With Self-attention Mechanism For Robust End-to-end Speech Recognition (2021)0.00
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
• Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00
• Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
• VSEGAN: Visual Speech Enhancement Generative Adversarial Network (2021)8.60