Df-conformer: Integrated Architecture Of Conv-tasnet And Conformer Using Linear Complexity Self-attention For Speech Enhancement

Abstract

Single-channel speech enhancement (SE) is an important task in speech processing. A widely used framework combines an analysis/synthesis filterbank with a mask prediction network, such as the Conv-TasNet architecture. In such systems, the denoising performance and computational efficiency are mainly affected by the structure of the mask prediction network. In this study, we aim to improve the sequential modeling ability of Conv-TasNet architectures by integrating Conformer layers into a new mask prediction network. To make the model computationally feasible, we extend the Conformer using linear complexity attention and stacked 1-D dilated depthwise convolution layers. We trained the model on 3,396 hours of noisy speech data, and show that (i) the use of linear complexity attention avoids high computational complexity, and (ii) our model achieves higher scale-invariant signal-to-noise ratio than the improved time-dilated convolution network (TDCN++), an extended version of Conv-TasNet.

Stats

• citations31
• S2 citations—
• github stars0
• HF likes0
• heat score11.29
• arxiv keykoizumi2021df

Related papers

• Efficient Encoder-decoder And Dual-path Conformer For Comprehensive Feature Learning In Speech Enhancement (2023)7.16
• 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
• Efficient Conformer: Progressive Downsampling And Grouped Attention For Automatic Speech Recognition (2021)13.79
• Inter-channel Conv-tasnet For Multichannel Speech Enhancement (2021)0.00
• Fast Conformer With Linearly Scalable Attention For Efficient Speech Recognition (2023)14.47
• PCNN: A Lightweight Parallel Conformer Neural Network For Efficient Monaural Speech Enhancement (2023)6.77
• TFCN: Temporal-frequential Convolutional Network For Single-channel Speech Enhancement (2022)0.00
• Uformer: A Unet Based Dilated Complex & Real Dual-path Conformer Network For Simultaneous Speech Enhancement And Dereverberation (2021)12.87