PJS: phoneme-balanced Japanese singing-voice corpus.

Junya Koguchi Shinnosuke Takamichi Masanori Morise

Published in: APSIPA (2020)

Keyphrases

speech synthesis
speech sounds
speech recognition
test set
text to speech
automatic speech recognition
open domain
japanese language
coreference resolution
manually annotated
acoustic features
information extraction
non stationary
supervised machine learning
prosodic features
spoken dialog