AWhat changed
Jointly trained convolutional audio encoding/decoding with residual vector quantization, reconstruction/adversarial losses and quantizer dropout to support several bitrates within one streamable model.
Scientific scope
Jointly trained convolutional audio encoding/decoding with residual vector quantization, reconstruction/adversarial losses and quantizer dropout to support several bitrates within one streamable model. Lossy perceptual coding, not exact waveform preservation. Subjective quality and smartphone real-time claims depend on the tested bandwidth, audio and implementation; residual quantization has predecessors.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Lossy perceptual coding, not exact waveform preservation. Subjective quality and smartphone real-time claims depend on the tested bandwidth, audio and implementation; residual quantization has predecessors.
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.
- SoundStream: An End-to-End Neural Audio Codec
- Zeghidour et al.: SoundStream scalable neural audio coding — author/company project record
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