A rate-distortion trained speech codec using a channel-wise entropy model and CNN-RWKV blocks reports 53.51% average BD-rate savings over four baselines.
Soundstream: An end-to-end neural audio codec,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rate-Aware Learned Speech Compression
A rate-distortion trained speech codec using a channel-wise entropy model and CNN-RWKV blocks reports 53.51% average BD-rate savings over four baselines.