Skip to main navigation
Skip to search
Skip to main content
Korea University Pure Home
Home
Profiles
Research units
Equipment
Research output
Press/Media
Search by expertise, name or affiliation
DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion
Ha Yeong Choi
, Sang Hoon Lee
,
Seong Whan Lee
*
*
Corresponding author for this work
Department of Artificial Intelligence
* World 2% Researchers
Research output
:
Contribution to journal
›
Conference article
›
peer-review
30
Citations (Scopus)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Voice Conversion
100%
Disentangled Representation
100%
Denoising Diffusion Models
100%
Style Transfer
40%
Timbre
20%
Generation Process
20%
Generative Models
20%
Diffusion Model
20%
All Levels
20%
Publicly Available
20%
Model Size
20%
Prior Distribution
20%
Data Distribution
20%
Mixed Style
20%
Small Animal Model
20%
Linguistic Information
20%
Audio Sample
20%
Conversion Model
20%
Speech Representation
20%
Voice Style Transfer
20%
Self-supervised Representations
20%
Diffusion-based Generative Models
20%
Intonation
20%
Speech Attributes
20%
Computer Science
de-noising
100%
Diffusion Model
100%
Generative Model
33%
Experimental Result
16%
Data Distribution
16%