Login / Signup
Using automatic stress extraction from audio for improved prosody modelling in speech synthesis.
György Szaszák
András Beke
Gábor Olaszy
Bálint Pál Tóth
Published in:
INTERSPEECH (2015)
Keyphrases
</>
speech synthesis
text to speech
prosodic features
speech recognition
speech corpus
speech music discrimination
vocal tract
multimedia
information extraction
pattern recognition
semi automatic
neural network
automatic extraction
word processing
speaker verification
language model
data mining