BWhat changed
Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource.
Scientific scope
Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource. Inherits speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.
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 speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.
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