Login / Signup
Investigating the Robustness of Sequence-to-Sequence Text-to-Speech Models to Imperfectly-Transcribed Training Data.
Jason Fong
Pilar Oplustil Gallegos
Zack Hodari
Simon King
Published in:
INTERSPEECH (2019)
Keyphrases
</>
training data
text to speech
general purpose
complex systems
data sets
prior knowledge
supervised learning
statistical models
learning algorithm
video sequences
pattern recognition
training set
classification accuracy
test set
learned models