Synthesizing fast speech by implementing multi-phone units in unit selection speech synthesis.

Donata Moers Igor Jauk Bernd Möbius Petra Wagner

Published in: SSW (2010)

Keyphrases

speech synthesis
speech recognition
text to speech
vocal tract
prosodic features
processing units
speech corpus
speech signal
pattern recognition
acoustic models
hidden markov models
data mining
automatic speech recognition
speech recognizer
selection algorithm
language model
image processing
machine learning