# Time-Frequency Attention for Monaural Speech Enhancement

arXiv: https://arxiv.org/abs/2111.07518 · HTML: https://mlsanity.com/paper/2111.07518/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2021.

## Built on by (most cited first, 2 of 2)

- [A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement](https://mlsanity.com/paper/2506.01023/) (2025)
- [Selective State Space Model for Monaural Speech Enhancement](https://mlsanity.com/paper/2411.06217/) (2024)

## Abstract (arXiv)

Most studies on speech enhancement generally don't consider the energy distribution of speech in time-frequency (T-F) representation, which is important for accurate prediction of mask or spectra. In this paper, we present a simple yet effective T-F attention (TFA) module, where a 2-D attention map is produced to provide differentiated weights to the spectral components of T-F representation. To validate the effectiveness of our proposed TFA module, we use the residual temporal convolution network (ResTCN) as the backbone network and conduct extensive experiments on two commonly used training targets. Our experiments demonstrate that applying our TFA module significantly improves the performance in terms of five objective evaluation metrics with negligible parameter overhead. The evaluation results show that the proposed ResTCN with the TFA module (ResTCN+TFA) consistently outperforms other baselines by a large margin.