PJS: phoneme-balanced Japanese singing voice corpus.

Junya Koguchi Shinnosuke Takamichi

Published in: CoRR (2020)

Keyphrases

speech synthesis
speech recognition
speech sounds
prosodic features
spontaneous speech
hidden markov models
text to speech
training corpus
context dependent
test set
spoken dialog
machine learning
manually annotated
music information retrieval
coreference resolution
text corpora
highly skewed
speaker dependent