BWhat changed
Inserted vector quantization into a multilingual recognition encoder to obtain supervised semantic tokens, coupling text-to-token language modeling with conditional-flow speech rendering.
Scientific scope
Inserted vector quantization into a multilingual recognition encoder to obtain supervised semantic tokens, coupling text-to-token language modeling with conditional-flow speech rendering. Inherits Whisper, quantization, language modeling and flow matching. Acquired delta is supervised speech-token interface and synthesis integration, not first semantic audio tokens. Voice-cloning benchmark gains are source-specific; no clone generated.
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 Whisper, quantization, language modeling and flow matching. Acquired delta is supervised speech-token interface and synthesis integration, not first semantic audio tokens. Voice-cloning benchmark gains are source-specific; no clone generated.
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