The paper introduces target-KL regularization to train audio VAEs at specific bitrates, enabling rate-distortion curves and comparison to discrete audio codecs for improved text-to-sound generation.
This allows for direct comparison to discrete neural audio codecs and enables systematic study of the rate-distortion trade-off for continuous audio compres- sion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Taming Audio VAEs via Target-KL Regularization
The paper introduces target-KL regularization to train audio VAEs at specific bitrates, enabling rate-distortion curves and comparison to discrete audio codecs for improved text-to-sound generation.