Improving speech synthesis quality by reducing pitch peaks in the source recordings.

Luisina Violante Pablo Rodríguez Zivic Agustín Gravano

Published in: HLT-NAACL (2013)

Keyphrases

speech synthesis
speech recognition
text to speech
high quality
improve quality
higher quality
low quality
prosodic features
neural network
learning algorithm
quality measures
vocal tract