# TridentSE: Guiding Speech Enhancement with 32 Global Tokens

arXiv: https://arxiv.org/abs/2210.12995 · HTML: https://mlsanity.com/paper/2210.12995/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2022.

## Built on by (most cited first, 4 of 4)

- [xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2501.06146/) (2025)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology](https://mlsanity.com/paper/2412.17778/) (2024)
- [SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios](https://mlsanity.com/paper/2606.25959/) (2026)

## Abstract (arXiv)

In this paper, we present TridentSE, a novel architecture for speech enhancement, which is capable of efficiently capturing both global information and local details. TridentSE maintains T-F bin level representation to capture details, and uses a small number of global tokens to process the global information. Information is propagated between the local and the global representations through cross attention modules. To capture both inter- and intra-frame information, the global tokens are divided into two groups to process along the time and the frequency axis respectively. A metric discriminator is further employed to guide our model to achieve higher perceptual quality. Even with significantly lower computational cost, TridentSE outperforms a variety of previous speech enhancement methods, achieving a PESQ of 3.47 on VoiceBank+DEMAND dataset and a PESQ of 3.44 on DNS no-reverb test set. Visualization shows that the global tokens learn diverse and interpretable global patterns.