HH-Codec reaches 24 tokens/s and 0.3 kbps for 24 kHz speech with single-quantizer inference and reports reconstruction metrics close to much higher-bandwidth codecs.
Multi-scale sub- band constant-q transform discriminator for high-fidelity vocoder
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling
HH-Codec reaches 24 tokens/s and 0.3 kbps for 24 kHz speech with single-quantizer inference and reports reconstruction metrics close to much higher-bandwidth codecs.