Embedded Scalars, Preferred Readings and Prosody: An Experimental Revisit.

Michael Franke Fabian Schlotterbeck Petra Augurzky

Published in: J. Semant. (2017)

Keyphrases

text to speech
neural network
databases
data structure
speech synthesis
real time
three dimensional
image sequences
preprocessing
watermarking algorithm
multi stream
synthesized speech