Syllable HMM based Mandarin TTS and comparison with concatenative TTS.

Zhiwei Shuang Shiyin Kang Qin Shi Yong Qin Lianhong Cai

Published in: INTERSPEECH (2009)

Keyphrases

prosodic features
text to speech
speech synthesis
speaker verification
hidden markov models
multiscale
spontaneous speech
quantitative evaluation
machine learning
feature selection
three dimensional
high level
multi modal
speech recognition
audio visual
word processing