A Mask Free Neural Network for Monaural Speech Enhancement

Liang Liu, Haixin Guan, Jinlong Ma, Wei Dai, Guangyong Wang +1 more
6/7/2023
cs.SDcs.AIeess.AS

No official code found. Best implementation: ioyy900205/MFNet (37 stars, MIT, last commit 2023-05-22). 1 more below.

Abstract

In speech enhancement, the lack of clear structural characteristics in the target speech phase requires the use of conservative and cumbersome network frameworks. It seems difficult to achieve competitive performance using direct methods and simple network architectures. However, we propose the MFNet, a direct and simple network that can not only map speech but also map reverse noise. This network is constructed by stacking global local former blocks (GLFBs), which combine the advantages of Mobileblock for global processing and Metaformer architecture for local interaction. Our experimental results demonstrate that our network using mapping method outperforms masking methods, and direct mapping of reverse noise is the optimal solution in strong noise environments. In a horizontal comparison on the 2020 Deep Noise Suppression (DNS) challenge test set without reverberation, to the best of our knowledge, MFNet is the current state-of-the-art (SOTA) mapping model.

View on arXivView PDF

Code Implementations(2)

ioyy900205/MFNetCommunity100%
MIT

This repo provides the processed samples of the manuscript "a Mask Free Neural Network for Monaural Speech Enhancement", which was accepted by INTERSPEECH2023.

3753 years agoMIT
taotaowang97479/MFNet-SpeechEnhancementCommunity62%

This is the unofficial implementation of MFNet, from paper''a Mask Free Neural Network for Monaural Speech Enhancement''

131Python1 years ago

Similar Papers

Unsupervised Noise adaptation using Data Simulation

81% match1 repo142023

Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance

80% match2024

Improving GANs for Speech Enhancement

80% match1 repo462020

Speech and Speaker Recognition from Raw Waveform with SincNet

80% match1 repo1.2k2018

SEGAN: Speech Enhancement Generative Adversarial Network

80% match1 repo8622017

VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders

79% match2024

Cite this paper

@article{liu2023mask,
  title  = {A Mask Free Neural Network for Monaural Speech Enhancement},
  author = {Liang Liu and Haixin Guan and Jinlong Ma and Wei Dai and Guangyong Wang and Shaowei Ding},
  year   = {2023},
  eprint = {2306.04286},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.04286v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.04286.svg)](https://codeofpaper.com/paper/2306.04286)

Discussion