PFlow-VC performs expressive voice conversion by conditioning a flow-matching Mel-spectrogram decoder on discrete speaker-normalized pitch tokens and a target speaker prompt, improving emotion style transfer.
Unsupervised speech decomposition via triple information bottleneck,
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
background 1representative citing papers
citing papers explorer
-
Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
PFlow-VC performs expressive voice conversion by conditioning a flow-matching Mel-spectrogram decoder on discrete speaker-normalized pitch tokens and a target speaker prompt, improving emotion style transfer.