BWhat changed
Used translation-model perplexity to derive word-level contextual delays in synthetic aligned speech pairs and trained a multistream decoder that jointly produces translation text and speech.
Scientific scope
Used translation-model perplexity to derive word-level contextual delays in synthetic aligned speech pairs and trained a multistream decoder that jointly produces translation text and speech. Inherits Moshi multistream architecture and neural translation. Tested original French-to-English system and selected device settings do not imply universal language coverage, professional-equivalent translation or zero-latency operation. Hibiki-Zero's later process-reward method is a separate technical delta.
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 Moshi multistream architecture and neural translation. Tested original French-to-English system and selected device settings do not imply universal language coverage, professional-equivalent translation or zero-latency operation. Hibiki-Zero's later process-reward method is a separate technical delta.
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