Log In Sign Up

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

by   Kanghao Zhang, et al.

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.


page 1

page 2

page 3

page 4


Speech Enhancement via Deep Spectrum Image Translation Network

Quality and intelligibility of speech signals are degraded under additiv...

ClearBuds: Wireless Binaural Earbuds for Learning-Based Speech Enhancement

We present ClearBuds, the first hardware and software system that utiliz...

Real Time Speech Enhancement in the Waveform Domain

We present a causal speech enhancement model working on the raw waveform...

INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing

The ConferencingSpeech 2021 challenge is proposed to stimulate research ...

Foster Strengths and Circumvent Weaknesses: a Speech Enhancement Framework with Two-branch Collaborative Learning

Recent single-channel speech enhancement methods usually convert wavefor...

Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression

This paper introduces a dual-signal transformation LSTM network (DTLN) f...

Real-time Streaming Wave-U-Net with Temporal Convolutions for Multichannel Speech Enhancement

In this paper, we describe the work that we have done to participate in ...