BWhat changed
Padded character text with filler tokens and trained flow-based mel infilling to support non-autoregressive zero-shot speech without explicit phoneme alignment/duration modules.
Scientific scope
Padded character text with filler tokens and trained flow-based mel infilling to support non-autoregressive zero-shot speech without explicit phoneme alignment/duration modules. Inherits flow matching, audio infilling and zero-shot TTS. Removing explicit alignment modules is not exact alignment or universal human-level speech; length handling and generation computation 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. Inherits flow matching, audio infilling and zero-shot TTS. Removing explicit alignment modules is not exact alignment or universal human-level speech; length handling and generation computation 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.
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