AWhat changed
Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt.
Scientific scope
Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt. Scope limitation: This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.
Contributors
- The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.
- Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper
- Wang and colleagues: VALL-E neural-codec language-model speech synthesis — company research page
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