Scaling of waveform segments along the time axis for concatenative speech synthesis.

Nobuyuki Nishizawa Hisashi Kawai

Published in: ICASSP (1) (2004)

Keyphrases

speech synthesis
speech recognition
text to speech
prosodic features
vocal tract
database
line segments
data sets
frequency domain
noisy environments
information retrieval
neural network
face recognition
multiscale
decision trees
knowledge base
image formation
automatic speech recognition
computer vision
data mining