DiffProsody: Diffusion-Based Latent Prosody Generation for Expressive Speech Synthesis With Prosody Conditional Adversarial Training

Author:

Oh Hyung-Seok1ORCID,Lee Sang-Hoon2ORCID,Lee Seong-Whan1ORCID

Affiliation:

1. Department of Artificial Intelligence, Korea University, Seoul, South Korea

2. Department of Software and Computer Engineering, Ajou University, Suwon-si, South Korea

Funder

Institute of Information and communications Technology Planning & Evaluation

Korea government

Artificial Intelligence Graduate School Program

Artificial Intelligence Innovation Hub

Artificial Intelligence Convergence Innovation Human Resources Development and Voice&Avatar, Naver Cloud, Seongnam, Korea

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Reference66 articles.

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

2. FastSpeech: Fast, robust and controllable text to speech;Ren,2019

3. FastSpeech 2: Fast and high-quality end-to-end text to speech;Ren,2021

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

5. PortaSpeech: Portable and high-quality generative text-to-speech;Ren,2021

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