# TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge

arXiv: https://arxiv.org/abs/2303.07704 · HTML: https://mlsanity.com/paper/2303.07704/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2023.

## Built on by (most cited first, 8 of 8)

- [LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement](https://mlsanity.com/paper/2503.00493/) (2025)
- [ReZero: Region-customizable Sound Extraction](https://mlsanity.com/paper/2308.16892/) (2023)
- [UniFlow: Unifying Speech Front-End Tasks via Continuous Generative Modeling](https://mlsanity.com/paper/2508.07558/) (2025)
- [High-Fidelity Speech Enhancement via Discrete Audio Tokens](https://mlsanity.com/paper/2510.02187/) (2025)
- [Personalized Speech Enhancement Without a Separate Speaker Embedding Model](https://mlsanity.com/paper/2406.09928/) (2024)
- [Post-Training Speech Enhancement Language Models with Perceptual Rewards](https://mlsanity.com/paper/2606.21458/) (2026)
- [Hybrid Real- and Complex-valued Neural Network Architecture](https://mlsanity.com/paper/2504.03497/) (2025)
- [StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios](https://mlsanity.com/paper/2609.03414/) (2026)

## Abstract (arXiv)

This paper introduces the Unbeatable Team's submission to the ICASSP 2023 Deep Noise Suppression (DNS) Challenge. We expand our previous work, TEA-PSE, to its upgraded version -- TEA-PSE 3.0. Specifically, TEA-PSE 3.0 incorporates a residual LSTM after squeezed temporal convolution network (S-TCN) to enhance sequence modeling capabilities. Additionally, the local-global representation (LGR) structure is introduced to boost speaker information extraction, and multi-STFT resolution loss is used to effectively capture the time-frequency characteristics of the speech signals. Moreover, retraining methods are employed based on the freeze training strategy to fine-tune the system. According to the official results, TEA-PSE 3.0 ranks 1st in both ICASSP 2023 DNS-Challenge track 1 and track 2.