Login / Signup
Cross-speaker style transfer for text-to-speech using data augmentation.
Manuel Sam Ribeiro
Julian Roth
Giulia Comini
Goeric Huybrechts
Adam Gabrys
Jaime Lorenzo-Trueba
Published in:
CoRR (2022)
Keyphrases
</>
data sets
synthetic data
raw data
sensor data
prior knowledge
data collection
original data
high dimensional data
statistical analysis
database
social networks
image data
data points
end users
training data
data distribution
clustering algorithm
data quality
text to speech