Papers › Adaptive Convolution for CNN-based Speech Enhancement Models

Adaptive Convolution for CNN-based Speech Enhancement Models

20 Feb 2025arXiv:2502.14224archive 2025-07-28

DaHan Wang, Xiaobin Rong, Shiruo Sun, Yuxiang Hu, Changbao Zhu, Jing Lu

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper, we introduce adaptive convolution, an efficient and versatile convolutional module that enhances the model's capability to adaptively represent speech signals. Adaptive convolution performs frame-wise causal dynamic convolution, generating time-varying kernels for each frame by assembling multiple parallel candidate kernels. A Lightweight attention mechanism leverages both current and historical information to assign adaptive weights to each candidate kernel, guiding their aggregation. This enables the convolution operation to adapt to frame-level speech spectral features, leading to more efficient extraction and reconstruction. Experimental results on various CNN-based models demonstrate that adaptive convolution significantly improves the performance with negligible increases in computational complexity, especially for lightweight models. Furthermore, we propose the adaptive convolutional recurrent network (AdaptCRN), an ultra-lightweight model that incorporates adaptive convolution and an efficient encoder-decoder design, achieving superior performance compared to models with similar or even higher computational costs.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderSpeech Enhancement

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionConvolutionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections