JIS is a new 169-speaker Japanese speech corpus of live idols, built to support listener-familiarity-based evaluation of TTS and VC speaker similarity.
The initial challenge in TTS and VC research is to generate voices of speakers included in training data [1]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
JIS: A Speech Corpus of Japanese Idol Speakers with Various Speaking Styles
JIS is a new 169-speaker Japanese speech corpus of live idols, built to support listener-familiarity-based evaluation of TTS and VC speaker similarity.