BWhat changed
Combined discrete audio-token language modeling with text conditioning and audio-mixture augmentation for compositional sound generation and continuation.
Scientific scope
Combined discrete audio-token language modeling with text conditioning and audio-mixture augmentation for compositional sound generation and continuation. Codec modeling, autoregression and classifier-free guidance are inherited. Original 2022 report controls the record; later AudioCraft/EnCodec integration is not backdated. Empirical perceptual results are not universal quality or rights guarantees.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Codec modeling, autoregression and classifier-free guidance are inherited. Original 2022 report controls the record; later AudioCraft/EnCodec integration is not backdated. Empirical perceptual results are not universal quality or rights guarantees.
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.
- AudioGen: Textually Guided Audio Generation
- Kreuk et al.: AudioGen text-conditioned sound generation — 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