Investigating Self-Supervised Learning for Speech Enhancement and Separation
Author:
Affiliation:
1. Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA
2. Carnegie Mellon University,USA
3. National Taiwan University,Taiwan
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9745891/9746004/09746303.pdf?arnumber=9746303
Reference60 articles.
1. Representation learning with contrastive predictive coding;van den oord,2018
2. TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
3. Self-supervised Learning: Generative or Contrastive
4. Self-supervised pre-training reduces label permutation instability of speech separation;huang,2020
5. SUPERB: Speech Processing Universal PERformance Benchmark
Cited by 38 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. Mongolian Pronunciation Data Enhancement Method Based on Separation Contrast Learning;2024 International Conference on Asian Language Processing (IALP);2024-08-04
2. Assessment of Self-Supervised Denoising Methods for Esophageal Speech Enhancement;Applied Sciences;2024-07-31
3. Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30
4. LeBenchmark 2.0: A standardized, replicable and enhanced framework for self-supervised representations of French speech;Computer Speech & Language;2024-06
5. Continuous lipreading based on acoustic temporal alignments;EURASIP Journal on Audio, Speech, and Music Processing;2024-05-06
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