Synthesizing Speech from ECoG with a Combination of Transformer-Based Encoder and Neural Vocoder
Author:
Affiliation:
1. Tokyo University of Agriculture and Technology,Graduate School of Engineering
2. Juntendo University School of Medicine,Department of Neurosurgery
3. Tokyo Institute of Technology,Department of Computer Science
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/10094559/10094560/10097004.pdf?arnumber=10097004
Reference25 articles.
1. Waveglow: A Flow-based Generative Network for Speech Synthesis
2. Wavenet: A Generative Model for Raw Audio;oord;arXiv 1609 03499,2016
3. Densely Connected Convolutional Networks
4. Speech synthesis from ECoG using densely connected 3D convolutional neural networks
5. Signal estimation from modified short-time Fourier transform
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. Speech Synthesis from Electrocorticogram During Imagined Speech Using a Transformer-Based Decoder and Pretrained Vocoder;2024-08-22
2. A User-Guided Generation Framework for Personalized Music Synthesis Using Interactive Evolutionary Computation;Proceedings of the Genetic and Evolutionary Computation Conference Companion;2024-07-14
3. Feasibility of decoding covert speech in ECoG with a Transformer trained on overt speech;Scientific Reports;2024-05-20
4. Subject-Agnostic Transformer-Based Neural Speech Decoding from Surface and Depth Electrode Signals;2024-03-14
5. Feasibility of decoding covert speech in ECoG with a Transformer trained on overt speech;2024-02-06
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