Any-to-Any Voice Conversion With Multi-Layer Speaker Adaptation and Content Supervision

Author:

Xu Xuexin1ORCID,Shi Liang1ORCID,Chen Xunquan2ORCID,Lin Pingyuan1ORCID,Lian Jie1ORCID,Chen Jinhui3ORCID,Zhang Zhihong1ORCID,Hancock Edwin R.4ORCID

Affiliation:

1. School of Informatics, Xiamen University, Xiamen, China

2. Graduate School of System Informatics, Kobe University, Kobe, Japan

3. Faculty of Systems Engineering, Wakayama University, Wakayama, Japan

4. Department of Computer Science, University of York, York, U.K.

Funder

National Natural Science Foundation of China

Fundamental Research Funds for the Central Universities

JSPS KAKENHI

Research Support Fund of Wakayama University

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

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

Reference58 articles.

1. VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net Architecture

2. AudioLM: A Language Modeling Approach to Audio Generation

3. Autovc: Zero-shot voice style transfer with only autoencoder loss;qian;Proc Int Conf Mach Learn,0

4. Visualizing data using t-sne;maaten;J Mach Learn Res,2008

5. Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations

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