A dual alignment scheme for improved speech-to-singing voice conversion.

Karthika Vijayan Minghui Dong Haizhou Li

Published in: APSIPA (2017)

Keyphrases

text to speech
speech recognition errors
speech recognition
data sets
emotion recognition
speech quality
pattern recognition
automatic speech recognition
detection scheme
fundamental frequency
improved algorithm
speech signal
image alignment
acoustic features
neural network
spontaneous speech