ProsoCodec models prosody as a conditional residual in a speech codec via text and speaker prefix conditioning, yielding improved prosody preservation and less timbre leakage in voice conversion experiments.
A unified neural codec language model for selective editable text to speech generation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion
ProsoCodec models prosody as a conditional residual in a speech codec via text and speaker prefix conditioning, yielding improved prosody preservation and less timbre leakage in voice conversion experiments.