Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data.

Seung Won Park Doo-young Kim Myun-chul Joe

Published in: CoRR (2020)

Keyphrases

data sets
data collection
image data
original data
data structure
training data
high quality
raw data
end users
missing data
data processing
input data
parallel algorithm
synthetic data
high dimensional data
computer systems
data points
data analysis
data streams
image sequences