Login / Signup
MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance.
Semin Kim
Myeonghun Jeong
Hyeonseung Lee
Minchan Kim
Byoung Jin Choi
Nam Soo Kim
Published in:
CoRR (2024)
Keyphrases
</>
supervised training
training data
test data
training samples
support vector machine
data sets
small number
unsupervised learning
decision trees
training process
pairwise
fuzzy logic
bp neural network
model selection
data points
prior knowledge
information retrieval