# Uformer: A Unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation

arXiv: https://arxiv.org/abs/2111.06015 · HTML: https://mlsanity.com/paper/2111.06015/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2021.

## Built on by (most cited first, 13 of 13)

- [BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embedding](https://mlsanity.com/paper/2408.06851/) (2024)
- [Noise robust speech emotion recognition with signal-to-noise ratio adapting speech enhancement](https://mlsanity.com/paper/2309.01164/) (2023)
- [Distil-DCCRN: A Small-footprint DCCRN Leveraging Feature-based Knowledge Distillation in Speech Enhancement](https://mlsanity.com/paper/2408.04267/) (2024)
- [Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition](https://mlsanity.com/paper/2307.02909/) (2023)
- [Linguistic Knowledge Transfer Learning for Speech Enhancement](https://mlsanity.com/paper/2503.07078/) (2025)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement](https://mlsanity.com/paper/2509.24708/) (2025)
- [Toward Real Flare Removal: A Comprehensive Pipeline and A New Benchmark](https://mlsanity.com/paper/2306.15884/) (2023)
- [Exploiting Time-Frequency Conformers for Music Audio Enhancement](https://mlsanity.com/paper/2308.12599/) (2023)
- [HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals](https://mlsanity.com/paper/2605.26190/) (2026)
- [Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge](https://mlsanity.com/paper/2402.01413/) (2024)
- [Comparison of Knowledge Distillation Methods for Low-complexity Multi-microphone Speech Enhancement using the FT-JNF Architecture](https://mlsanity.com/paper/2507.19208/) (2025)
- [CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-Car Speech Separation with Distributed Heterogeneous Arrays](https://mlsanity.com/paper/2509.01399/) (2025)

## Abstract (arXiv)

Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation. Traditional approaches always treat these two features separately, ignoring their underlying relationship. In this paper, we propose Uformer, a Unet based dilated complex & real dual-path conformer network in both complex and magnitude domain for simultaneous speech enhancement and dereverberation. We exploit time attention (TA) and dilated convolution (DC) to leverage local and global contextual information and frequency attention (FA) to model dimensional information. These three sub-modules contained in the proposed dilated complex & real dual-path conformer module effectively improve the speech enhancement and dereverberation performance. Furthermore, hybrid encoder and decoder are adopted to simultaneously model the complex spectrum and magnitude and promote the information interaction between two domains. Encoder decoder attention is also applied to enhance the interaction between encoder and decoder. Our experimental results outperform all SOTA time and complex domain models objectively and subjectively. Specifically, Uformer reaches 3.6032 DNSMOS on the blind test set of Interspeech 2021 DNS Challenge, which outperforms all top-performed models. We also carry out ablation experiments to tease apart all proposed sub-modules that are most important.