A single neural audio codec can operate at multiple token temporal resolutions by generating TTR-dependent convolutional kernels from shared parameters while adjusting kernel size and stride.
Zimtohrli: An efficient psychoacoustic audio sim- ilarity metric,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Audio Codec with Adjustable Token Temporal Resolution Using Sampling-Frequency-Independent Convolutional Layers
A single neural audio codec can operate at multiple token temporal resolutions by generating TTR-dependent convolutional kernels from shared parameters while adjusting kernel size and stride.