Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data.

Yusheng Tian Wei Liu Tan Lee

Published in: ASRU (2023)

Keyphrases

data sets
data structure
raw data
original data
computer systems
prior knowledge
data sources
speech synthesis
database
data collection
image data
end users
databases
input data
data analysis
high quality
statistical analysis
training data
face recognition
data quality
pattern analysis