Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction
Author:
Affiliation:
1. The Ohio State University,USA
2. Microsoft Corporation
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9745891/9746004/09746220.pdf?arnumber=9746220
Reference31 articles.
1. Unsupervised sound separation using mixture invariant training;wisdom;Proceedings of NeurIPS,2020
2. The rwth/upb/forth system combination for the 4th chime challenge evaluation;menne;Computer Speech & Language,2016
3. Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN
4. An Unsupervised Autoregressive Model for Speech Representation Learning
5. Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
Cited by 17 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. Improving Multi-Type License Plate Recognition via Learning Globally and Contrastively;IEEE Transactions on Intelligent Transportation Systems;2024-09
2. Audio-visual speech synthesis using vision transformer–enhanced autoencoders with ensemble of loss functions;Applied Intelligence;2024-03
3. Masked Modeling Duo: Towards a Universal Audio Pre-Training Framework;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024
4. Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024
5. IFF-WAV2VEC: Noise Robust Low-Resource Speech Recognition Based on Self-supervised Learning and Interactive Feature Fusion;2023 6th Artificial Intelligence and Cloud Computing Conference (AICCC);2023-12-16
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