A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings

Author:

Moliner Eloi1,Valimaki Vesa1

Affiliation:

1. Aalto University,Acoustics Lab,Dept. Signal Processing and Acoustics,Espoo,Finland,FI-02150

Publisher

IEEE

Reference27 articles.

1. Audio super-resolution using neural networks;kuleshov;Proc ICLR,2017

2. GACELA: A Generative Adversarial Context Encoder for Long Audio Inpainting of Music

3. Exploiting time-frequency patterns with LSTM-RNNs for low-bitrate audio restoration

4. Learning to denoise historical music;li;Proc 21st ISMIR Conf,2020

5. Learning features of music from scratch;thickstun;Proc ICLR,2017

Cited by 7 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

1. Location as Supervision for Weakly Supervised Multi-Channel Source Separation of Machine Sounds;2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA);2023-10-22

2. Multi-Stage Progressive Audio Bandwidth Extension;2022 IEEE Spoken Language Technology Workshop (SLT);2023-01-09

3. BirdSoundsDenoising: Deep Visual Audio Denoising for Bird Sounds;2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2023-01

4. BEHM-GAN: Bandwidth Extension of Historical Music Using Generative Adversarial Networks;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2023

5. DeepLabV3+ Vision Transformer for Visual Bird Sound Denoising;IEEE Access;2023

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