BWhat changed
Combined a low-rate continuous speech tokenizer with next-token diffusion to model long-form, multi-speaker speech within a language-model context.
Scientific scope
Combined a low-rate continuous speech tokenizer with next-token diffusion to model long-form, multi-speaker speech within a language-model context. Next-token diffusion is inherited. Duration, compression and speaker capacity are reported configurations, not guaranteed dialogue quality. Original synthesis report excludes later ASR/streaming variants; voice consent and impersonation risks remain.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Next-token diffusion is inherited. Duration, compression and speaker capacity are reported configurations, not guaranteed dialogue quality. Original synthesis report excludes later ASR/streaming variants; voice consent and impersonation risks remain.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- VibeVoice Technical Report
- Peng et al.: VibeVoice compressed continuous speech generation — official project source
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction