StarVC is an autoregressive voice conversion model that generates text tokens before acoustic tokens, improving linguistic fidelity while retaining speaker similarity.
System Architecture Our proposed StarVC framework is designed to jointly model speech conversion and text generation in an auto-regressive manner
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion
StarVC is an autoregressive voice conversion model that generates text tokens before acoustic tokens, improving linguistic fidelity while retaining speaker similarity.