AWhat changed
Introduced a deep autoregressive model that generates raw audio waveforms sample by sample, with applications to text-to-speech and music generation.
Scientific scope
Introduced a deep autoregressive model that generates raw audio waveforms sample by sample, with applications to text-to-speech and music generation. Scope limitation: The 2016 paper is a model architecture and reported experiments, not evidence that the original sample-by-sample system was real-time or replaced all speech synthesis systems.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. The 2016 paper is a model architecture and reported experiments, not evidence that the original sample-by-sample system was real-time or replaced all speech synthesis systems.
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.
- van den Oord and colleagues: WaveNet raw-audio generation — original paper
- van den Oord and colleagues: WaveNet raw-audio generation — 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