NanoCodec achieves competitive speech quality at 12.5 frames per second and 0.6-1.78 kbps, with a causal decoder for low-latency speech LLM inference.
Experiments setup To assess the performance of our codec in comparison to the LFSC and explore the effects of bitrate reduction, we adopted Koel-TTS [4], a SOTA LLM-based TTS model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference
NanoCodec achieves competitive speech quality at 12.5 frames per second and 0.6-1.78 kbps, with a causal decoder for low-latency speech LLM inference.