P2PSynCodec replaces residual vector quantization with a plain-to-pseudo synergistic scheme that transmits only one VQ codebook index and predicts the rest, cutting bitrate by a factor of four while preserving quality.
One quantizer is enough: Toward a lightweight audio codec,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
VoCodec achieves better performance than baselines at 1.1 kbps on LibriTTS by embedding voicing-driven quantization that reduces bitrate by ~27% versus uniform allocation.
citing papers explorer
-
An Ultra-Low-Bitrate Neural Speech Codec with Plain-to-Pseudo Synergistic Vector Quantization
P2PSynCodec replaces residual vector quantization with a plain-to-pseudo synergistic scheme that transmits only one VQ codebook index and predicts the rest, cutting bitrate by a factor of four while preserving quality.
-
VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization
VoCodec achieves better performance than baselines at 1.1 kbps on LibriTTS by embedding voicing-driven quantization that reduces bitrate by ~27% versus uniform allocation.