Login / Signup
My voice, your prosody: sharing a speaker specific prosody model across speakers in unit selection TTS.
Matthew P. Aylett
Justin Fackrell
Peter Rutten
Published in:
INTERSPEECH (2003)
Keyphrases
</>
text to speech
high level
probabilistic model
computational model
statistical model
cost function
mathematical model
information retrieval
theoretical framework
pattern recognition
speech recognition
input data
hidden markov models
selection algorithm
selection mechanism
neural network
speech synthesis