AWhat changed
Trained a non-autoregressive flow-matching model to infill speech from transcript and surrounding audio, enabling multiple synthesis and editing tasks through contextual conditioning.
Scientific scope
Trained a non-autoregressive flow-matching model to infill speech from transcript and surrounding audio, enabling multiple synthesis and editing tasks through contextual conditioning. Flow Matching is inherited; the contribution is the scalable speech-infilling system. The original release supplied a paper and demonstrations, rather than public model weights or code. Voice imitation requires consent and safeguards against impersonation.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Flow Matching is inherited; the contribution is the scalable speech-infilling system. The original release supplied a paper and demonstrations, rather than public model weights or code. Voice imitation requires consent and safeguards against impersonation.
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.
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
- Le et al.: Voicebox flow-matching speech infilling — institutional/author 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