U-former: Improving Monaural Speech Enhancement With Multi-head Self And Cross Attention

Abstract

For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking a target speaker, this paper treats the speech enhancement as sequence-to-sequence mapping, and propose a novel monaural speech enhancement U-net structure based on Transformer, dubbed U-Former. The key idea is to model long-term correlations and dependencies, which are crucial for accurate noisy speech modeling, through the multi-head attention mechanisms. For this purpose, U-Former incorporates multi-head attention mechanisms at two levels: 1) a multi-head self-attention module which calculate the attention map along both time- and frequency-axis to generate time and frequency sub-attention maps for leveraging global interactions between encoder features, while 2) multi-head cross-attention module which are inserted in the skip connections allows

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxu2022u

Related papers

• Uformer: A Unet Based Dilated Complex & Real Dual-path Conformer Network For Simultaneous Speech Enhancement And Dereverberation (2021)12.87
• Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00
• Mossformer: Pushing The Performance Limit Of Monaural Speech Separation Using Gated Single-head Transformer With Convolution-augmented Joint Self-attentions (2023)13.55
• Dilated U-net Based Approach For Multichannel Speech Enhancement From First-order Ambisonics Recordings (2020)0.00
• D2former: A Fully Complex Dual-path Dual-decoder Conformer Network Using Joint Complex Masking And Complex Spectral Mapping For Monaural Speech Enhancement (2023)0.00
• Self Multi-head Attention For Speaker Recognition (2019)13.84
• PCNN: A Lightweight Parallel Conformer Neural Network For Efficient Monaural Speech Enhancement (2023)6.77
• Monaural Speech Enhancement Using A Multi-branch Temporal Convolutional Network (2019)3.58