NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality

Author:

Tan Xu1ORCID,Chen Jiawei2ORCID,Liu Haohe3ORCID,Cong Jian2ORCID,Zhang Chen2ORCID,Liu Yanqing2ORCID,Wang Xi2ORCID,Leng Yichong4ORCID,Yi Yuanhao2ORCID,He Lei2ORCID,Zhao Sheng2ORCID,Qin Tao4ORCID,Soong Frank4ORCID,Liu Tie-Yan4ORCID

Affiliation:

1. Peking University, Beijing, China

2. Microsoft Azure Speech, Beijing, China

3. University of Surrey, Guildford, U.K.

4. Microsoft Research Asia, Beijing, China

Funder

British Broadcasting Corporation Research and Development

Engineering and Physical Sciences Research Council

Centre for Vision, Speech and Signal Processing

Faculty of Engineering and Physical Science

University of Surrey

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Reference60 articles.

1. A survey on neural speech synthesis;Tan,2021

2. WaveNet: A generative model for raw audio;van den Oord,2016

3. Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions

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

5. Deep voice: Real-time neural text-to-speech;Ö Arık

Cited by 12 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. An embedded end-to-end voice assistant;Engineering Applications of Artificial Intelligence;2024-10

2. Using Transfer Learning to Realize Low Resource Dungan Language Speech Synthesis;Applied Sciences;2024-07-20

3. 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

4. tinyDigiClones: A Multi-Modal LLM-Based Framework for Edge-optimized Personalized Avatars;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. The Proposal of Countermeasures for DeepFake Voices on Social Media Considering Waveform and Text Embedding;Annals of Emerging Technologies in Computing;2024-04-01

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