U-Style: Cascading U-Nets With Multi-Level Speaker and Style Modeling for Zero-Shot Voice Cloning-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

U-Style: Cascading U-Nets With Multi-Level Speaker and Style Modeling for Zero-Shot Voice Cloning

Published:2024 Issue: Volume:32 Page:4026-4035
ISSN:2329-9290
Container-title:IEEE/ACM Transactions on Audio, Speech, and Language Processing
language:
Short-container-title:IEEE/ACM Trans. Audio Speech Lang. Process.

Author:

Li Tao¹^ORCID,Wang Zhichao¹^ORCID,Zhu Xinfa¹^ORCID,Cong Jian²,Tian Qiao²^ORCID,Wang Yuping²,Xie Lei¹^ORCID

Affiliation:

1. School of Computer Science, Northwestern Polytechnical University, Xi'an, China

2. Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx8/6570655/10304349/10669040.pdf?arnumber=10669040

Reference48 articles.

1. Tacotron: Towards End-to-End Speech Synthesis

2. Deep voice 3: 2000-speaker neural text-to-speech;Ping,2018

3. Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis

4. The Multi-Speaker Multi-Style Voice Cloning Challenge 2021

5. SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech

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