Skip to content
conftrace_
2022 IJCAI IJCAI 2022

EditSinger: Zero-Shot Text-Based Singing Voice Editing System with Diverse Prosody Modeling

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Lichao Zhang, Zhou Zhao, Yi Ren, Liqun Deng

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Zero-Shot Learning

Keywords

zero-shot learning prosody modeling singing voice pitch prediction
Download PDF

More from IJCAI 2022

All IJCAI 2022 papers →
High-resource Language-specific Training for Multilingual Neural Machine Translation
SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speech
Clickbait Detection via Contrastive Variational Modelling of Text and Label
“Think Before You Speak”: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs
Charge Prediction by Constitutive Elements Matching of Crimes
CauAIN: Causal Aware Interaction Network for Emotion Recognition in Conversations