A conditional variational autoencoder with inverse autoregressive flow generates diverse intonations in voice conversion by sampling a latent style vector conditioned on phoneme posteriorgrams.
Naturally, there has been many studies on building a voice conversion machine that converts the source speakers voice into that of a target speakers automatically
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Voice Conversion with Diverse Intonation using Conditional Variational Auto-Encoder
A conditional variational autoencoder with inverse autoregressive flow generates diverse intonations in voice conversion by sampling a latent style vector conditioned on phoneme posteriorgrams.