Integrating Uncertainty Into Neural Network-Based Speech Enhancement

Author:

Fang Huajian1ORCID,Becker Dennis2ORCID,Wermter Stefan2ORCID,Gerkmann Timo1ORCID

Affiliation:

1. Signal Processing Group, Department of Informatics, Universität Hamburg, Hamburg, Germany

2. Knowledge Technology Group, Department of Informatics, Universität Hamburg, Hamburg, Germany

Funder

German Research Foundation DFG

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Acoustics and Ultrasonics,Computer Science (miscellaneous),Computational Mathematics

Reference78 articles.

1. Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech

2. Ensemble learning for speech enhancement;roux;Proc IEEE Workshop Appl Signal Proc Audio Acoust,0

3. Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

4. Bayesian SegNet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding;alex;Proc Brit Mach Vis Conf,2017

5. Guided Variational Autoencoder for Speech Enhancement with a Supervised Classifier

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3