Login / Signup
A tone-modeling technique using a quantized F0 context to improve tone correctness in average-voice-based speech synthesis.
Vataya Chunwijitra
Takashi Nose
Takao Kobayashi
Published in:
Speech Commun. (2012)
Keyphrases
</>
speech synthesis
text to speech
speech recognition
contextual information
context sensitive
prosodic features
neural network
context aware
modeling method
vocal tract
information retrieval
image processing
language model
conceptual model
standard deviation