# DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement

arXiv: https://arxiv.org/abs/2105.02436 · HTML: https://mlsanity.com/paper/2105.02436/

## Key facts

- Cited by 2 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 6 May 2021.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Interspeech 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2101.01902/) (2021)
- [A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement](https://mlsanity.com/paper/1709.08243/) (2017)
- [Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement](https://mlsanity.com/paper/2001.10601/) (2020)
- [Dense CNN with Self-Attention for Time-Domain Speech Enhancement](https://mlsanity.com/paper/2009.01941/) (2020)
- [Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform](https://mlsanity.com/paper/2102.04629/) (2021)
- [Subjective Evaluation of Noise Suppression Algorithms in Crowdsourcing](https://mlsanity.com/paper/2010.13200/) (2020)

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

- [ForkNet: Simultaneous Time and Time-Frequency Domain Modeling for Speech Enhancement](https://mlsanity.com/paper/2305.08292/) (2023)
- [MDDM: A Multi-view Discriminative Enhanced Diffusion-based Model for Speech Enhancement](https://mlsanity.com/paper/2505.13029/) (2025)

## Abstract (arXiv)

In real acoustic environment, speech enhancement is an arduous task to improve the quality and intelligibility of speech interfered by background noise and reverberation. Over the past years, deep learning has shown great potential on speech enhancement. In this paper, we propose a novel real-time framework called DBNet which is a dual-branch structure with alternate interconnection. Each branch incorporates an encoder-decoder architecture with skip connections. The two branches are responsible for spectrum and waveform modeling, respectively. A bridge layer is adopted to exchange information between the two branches. Systematic evaluation and comparison show that the proposed system substantially outperforms related algorithms under very challenging environments. And in INTERSPEECH 2021 Deep Noise Suppression (DNS) challenge, the proposed system ranks the top 8 in real-time track 1 in terms of the Mean Opinion Score (MOS) of the ITU-T P.835 framework.